This page lists some of our publications and preprints since 2015. More complete lists of publications are available from the personal websites of lab members.

2024

1. ACL

   Harnessing Toulmin’s theory for zero-shot argument explication

   Ankita Gupta, Ethan Zuckerman, and Brendan O’Connor

   In Association for Computational Linguistics, 2024
2. ACL

   LaMP: When Large Language Models Meet Personalization

   Alireza Salemi, Sheshera Mysore, Michael Bendersky, and Hamed Zamani

   In Association for Computational Linguistics, 2024
3. ACL

   Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation

   Jiachen Zhao, Wenlong Zhao, Andrew Drozdov, Benjamin Rozonoyer, Md Arafat Sultan, Jay-Yoon Lee, Mohit Iyyer, and Andrew McCallum

   In Association for Computational Linguistics, 2024
4. ACL

   SyllabusQA: A Course Logistics Question Answering Dataset

   Nigel Fernandez, Alexander Scarlatos, and Andrew Lan

   In Association for Computational Linguistics, 2024
5. ACL Findings

   The State of Relation Extraction Data Quality: Is Bigger Always Better?

   Erica Cai and Brendan O’Connor

   In Findings of the Association for Computational Linguistics, 2024
6. ACL Findings

   Aligning Large Multimodal Models with Factually Augmented RLHF

   Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liangyan Gui, Yu-Xiong Wang, Yiming Yang, Kurt Keutzer, and Trevor Darrell

   In Findings of the Association for Computational Linguistics: ACL, 2024
7. BEA

   Improving Automated Distractor Generation for Math Multiple-choice Questions with Overgenerate-and-rank

   Alexander Scarlatos, Wanyong Feng, Andrew Lan, Simon Woodhead, and Digory Smith

   In 9th Workshop on Innovative Use of NLP for Building Educational Applications (BEA), 2024
8. BEA

   Improving Socratic Question Generation using Data Augmentation and Preference Optimization

   Nischal Ashok Kumar and Andrew Lan

   In 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA), 2024
9. COLM

   Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images

   Ali Naseh, Katherine Thai, Mohit Iyyer, and Amir Houmansadr

   In Conference on Language Modeling, 2024
10. COLM

    FABLES: Evaluating faithfulness and content selection in book-length summarization

    Yekyung Kim, Yapei Chang, Marzena Karpinska, Aparna Garimella, Varun Manjunatha, Kyle Lo, Tanya Goyal, and Mohit Iyyer

    In Conference on Language Modeling, 2024
11. EACL

    PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents

    Simeng Sun, Yang Liu, Shuohang Wang, Chenguang Zhu, and Mohit Iyyer

    In European Chapter of the Association for Computational Linguistics, 2024
12. EACL Findings

    How Does In-Context Learning Help Prompt Tuning?

    Simeng Sun, Yang Liu, Dan Iter, Chenguang Zhu, and Mohit Iyyer

    In Findings of the Association for Computational Linguistics: EACL, 2024
13. ICLR

    BooookScore: A systematic exploration of book-length summarization in the era of LLMs

    Yapei Chang, Kyle Lo, Tanya Goyal, and Mohit Iyyer

    In International Conference on Learning Representations, 2024
14. J. Politics

    Meet the Press: Gendered Conversational Norms in Televised Political Discussion

    Daniel Naftel, Jon Green, Jared Edgerton, Mallory Wagner, Kelsey Shoub, and Skyler Cranmer

    Forthcoming, Journal of Politics, 2024
15. JLC

    "Let Me Just Interrupt You": Estimating Gender Effects in Supreme Court Oral Arguments

    Erica Cai, Ankita Gupta, Katherine Keith, Brendan O’Connor, and Douglas R. Rice

    Forthcoming, Journal of Law and Courts, 2024
16. ML4AL

    Latin Treebanks in Review: An Evaluation of Morphological Tagging Across Time

    Marisa Hudspeth, Brendan O’Connor, and Laure Thompson

    In 1st Workshop on Machine Learning for Ancient Languages (ML4AL), 2024
17. NAACL

    TopicGPT: A Prompt-based Topic Modeling Framework

    Chau Minh Pham, Alexander Hoyle, Simeng Sun, Philip Resnik, and Mohit Iyyer

    In North American Chapter of the Association for Computational Linguistics, 2024
18. NAACL Findings

    ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification

    Yaxin Zhu and Hamed Zamani

    In Findings of the Association for Computational Linguistics: NAACL, 2024
19. NAACL Findings

    Exploring Automated Distractor Generation for Math Multiple-choice Questions via Large Language Models

    Wanyong Feng, Jaewook Lee, Hunter McNichols, Alexander Scarlatos, Digory Smith, Simon Woodhead, Nancy Ornelas, and Andrew Lan

    In Findings of the Association for Computational Linguistics: NAACL, 2024
20. NAACL Findings

    GEE! Grammar Error Explanation with Large Language Models

    Yixiao Song, Kalpesh Krishna, Rajesh Bhatt, Kevin Gimpel, and Mohit Iyyer

    In Findings of the Association for Computational Linguistics: NAACL 2024, 2024
21. NLP+CSS

    Where on Earth Do Users Say They Are?: Geo-Entity Linking for Noisy Multilingual User Input

    Tessa Masis and Brendan O’Connor

    In Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS), 2024
22. NVSQ

    Who Leads and Who Echoes? Tracing Message Similarity Network of #ClimateChange Advocacy on Twitter

    Viviana Chiu Sik Wu and Weiai Wayne Xu

    In Nonprofit and Voluntary Sector Quarterly, 2024
23. PRQ

    Measuring Partisanship in Congressional Speech

    Jon Green, Kelsey Shoub, Rachel Blum, and Lindsey Cormack

    Political Research Quarterly, 2024
24. Personalization

    RAGs to Style: Personalizing LLMs with Style Embeddings

    Abhiman Neelakanteswara, Shreyas Chaudhari, and Hamed Zamani

    In 1st Workshop on Personalization of Generative AI Systems (PERSONALIZE), 2024
25. WSDM

    To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders

    Haw-Shiuan Chang, Nikhil Agarwal, and Andrew McCallum

    In The 17th ACM International Conference on Web Search and Data Mining (WSDM) , 2024
26. WWW

    Triage of Messages and Conversations in a Large-Scale Child Victimization Corpus

    Prasanna Lakkur Subramanyam, Mohit Iyyer, and Brian Levine

    In Proceedings of ACM The Web Conference (Web4Good Track), 2024

2023

1. ACL

   A Critical Evaluation of Evaluations for Long-form Question Answering

   Fangyuan Xu, Yixiao Song, Mohit Iyyer, and Eunsol Choi

   In Association of Computational Linguistics, 2023
2. ACL

   NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models

   Kai Mei, Zheng Li, Zhenting Wang, Yang Zhang, and Shiqing Ma

   In Association for Computational Linguistics, 2023
3. ACL

   Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling

   Haw-Shiuan Chang, Ruei-Yao Sun, Kathryn Ricci, and Andrew McCallum

   In Association of Computational Linguistics, 2023
4. ACL

   Evaluating Zero-Shot Event Structures: Recommendations for Automatic Content Extraction (ACE) Annotations

   Erica Cai and Brendan O’Connor

   In Association of Computational Linguistics, 2023
5. ACL

   Tree-Based Representation and Generation of Natural and Mathematical Language

   Alexander Scarlatos and Andrew Lan

   In Association for Computational Linguistics, 2023
6. ACL

   Interpretable Math Word Problem Solution Generation via Step-by-step Planning

   Mengxue Zhang, Zichao Wang, Zhichao Yang, Weiqi Feng, and Andrew Lan

   In Association for Computational Linguistics, 2023
7. ACL Findings

   Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond

   Haw-Shiuan Chang, Zonghai Yao, Alolika Gon, Hong Yu, and Andrew McCallum

   In Findings of Association of Computational Linguistics, 2023
8. ACL Findings

   JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions

   Mo Yu, Yi Gu, Xiaoxiao Guo, Yufei Feng, Xiaodan Zhu, Michael Greenspan, Murray Campbell, and Chuang Gan

   In Findings of the Association for Computational Linguistics: ACL, 2023
9. ACL Findings

   FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation

   Tu Vu, Mohit Iyyer, Xuezhi Wang, Noah Constant, Jerry Wei, Jason Wei, Chris Tar, Yun-Hsuan Sung, Denny Zhou, Quoc Le, and Thang Luong

   In Findings of the Association for Computational Linguistics, 2023
10. ACL Findings

    Causal Matching with Text Embeddings: A Case Study in Estimating the Causal Effects of Peer Review Policies

    Raymond Zhang, Neha Nayak Kennard, Daniel Smith, Daniel McFarland, Andrew McCallum, and Katherine Keith

    In Findings of Association of Computational Linguistics, 2023
11. BEA

    Improving Reading Comprehension Question Generation with Data Augmentation and Overgenerate-and-rank

    Nischal Ashok Kumar, Nigel Fernandez, Zichao Wang, and Andrew Lan

    In 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA), 2023
12. EACL

    LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization

    Kalpesh Krishna, Erin Bransom, Bailey Kuehl, Mohit Iyyer, Pradeep Dasigi, Arman Cohan, and Kyle Lo

    In European Chapter of the Association for Computational Linguistics, 2023
13. EACL Findings

    ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution

    Ankita Gupta, Marzena Karpinska, Wenlong Zhao, Kalpesh Krishna, Jack Merullo, Luke Yeh, Mohit Iyyer, and Brendan O’Connor

    In Findings of European Chapter of the Association for Computational Linguistics, 2023
14. EMNLP

    KNN-LM Does Not Improve Open-ended Text Generation

    Shufan Wang, Yixiao Song, Andrew Drozdov, Aparna Garimella, Varun Manjunatha, and Mohit Iyyer

    In EMNLP, 2023
15. EMNLP

    Sparse Universal Transformer

    Shawn Tan, Yikang Shen, Zhenfang Chen, Aaron Courville, and Chuang Gan

    In Empirical Methods in Natural Language Processing, 2023
16. EMNLP

    FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation

    Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Wei Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi

    In EMNLP, 2023
17. EMNLP Findings

    Machine Reading Comprehension using Case-based Reasoning

    Dung Thai, Dhruv Agarwal, Mudit Chaudhary, Wenlong Zhao, Rajarshi Das, Manzil Zaheer, Jay-Yoon Lee, Hannaneh Hajishirzi, and Andrew McCallum

    In Findings of the Association for Computational Linguistics: EMNLP, 2023
18. EMNLP Findings

    Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition

    Nishant Yadav, Nicholas Monath, Manzil Zaheer, and Andrew McCallum

    In Findings of the Association for Computational Linguistics: EMNLP, 2023
19. EMNLP Findings

    PaRaDe: Passage Ranking using Demonstrations with LLMs

    Andrew Drozdov, Honglei Zhuang, Zhuyun Dai, Zhen Qin, Razieh Rahimi, Xuanhui Wang, Dana Alon, Mohit Iyyer, Andrew McCallum, Donald Metzler, and Kai Hui

    In Findings of EMNLP, 2023
20. EMNLP Findings

    Disco Elysium: Exploring Player Perceptions of LLM-Generated Dialogue within a Commercial Video Game

    Nader Akoury, Qian Yang, and Mohit Iyyer

    In Findings of EMNLP, 2023
21. EMNLP Findings

    Conditional Natural Language Inference

    Youngwoo Kim, Razieh Rahimi, and James Allan

    In Findings of the Association for Computational Linguistics: EMNLP, 2023
22. Instruction

    A Monte Carlo Language Model Pipeline for Zero-Shot Sociopolitical Event Extraction

    Erica Cai and Brendan O’Connor

    2023
23. NeurIPS

    Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense

    Kalpesh Krishna, Yixiao Song, Marzena Karpinska, John Wieting, and Mohit Iyyer

    In Conference on Neural Information Processing Systems, 2023
24. WMT

    Large language models effectively leverage document-level context for literary translation, but critical errors persist

    Marzena Karpinska and Mohit Iyyer

    In WMT, 2023

2022

1. AAAI

   Sublinear Time Approximation of Text Similarity Matrices

   Archan Ray, Nicholas Monath, Andrew McCallum, and Cameron Musco

   In Proceedings of the AAAI Conference on Artificial Intelligence, 2022
2. AAAI

   An Evaluative Measure of Clustering Methods Incorporating Hyperparameter Sensitivity

   Siddhartha Mishra, Nicholas Monath, Michael Boratko, Ariel Kobren, and Andrew McCallum

   Proceedings of the AAAI Conference on Artificial Intelligence, 2022
3. ACL

   Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions

   Haw-Shiuan Chang and Andrew McCallum

   In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

   Neural language models (LMs) such as GPT-2 estimate the probability distribution over the next word by a softmax over the vocabulary. The softmax layer produces the distribution based on the dot products of a single hidden state and the embeddings of words in the vocabulary. However, we discover that this single hidden state cannot produce all probability distributions regardless of the LM size or training data size because the single hidden state embedding cannot be close to the embeddings of all the possible next words simultaneously when there are other interfering word embeddings between them. In this work, we demonstrate the importance of this limitation both theoretically and practically. Our work not only deepens our understanding of softmax bottleneck and mixture of softmax (MoS) but also inspires us to propose multi-facet softmax (MFS) to address the limitations of MoS. Extensive empirical analyses confirm our findings and show that against MoS, the proposed MFS achieves two-fold improvements in the perplexity of GPT-2 and BERT.

4. ACL

   RELiC: Retrieving Evidence for Literary Claims

   Katherine Thai, Yapei Chang, Kalpesh Krishna, and Mohit Iyyer

   In Association of Computational Linguistics, 2022
5. ACL

   Event-Event Relation Extraction using Probabilistic Box Embedding

   EunJeong Hwang, Jay-Yoon Lee, Tianyi Yang, Dhruvesh Patel, Dongxu Zhang, and Andrew McCallum

   In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2022

   To understand a story with multiple events, it is important to capture the proper relations across these events. However, existing event relation extraction (ERE) framework regards it as a multi-class classification task and do not guarantee any coherence between different relation types, such as anti-symmetry. If a phone line “died” after “storm”, then it is obvious that the “storm” happened before the “died”. Current framework of event relation extraction do not guarantee this coherence and thus enforces it via constraint loss function (Wang et al., 2020). In this work, we propose to modify the underlying ERE model to guarantee coherence by representing each event as a box representation (BERE) without applying explicit constraints. From our experiments, BERE also shows stronger conjunctive constraint satisfaction while performing on par or better in F1 compared to previous models with constraint injection.

6. ACL

   Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings

   Shib Dasgupta, Michael Boratko, Siddhartha Mishra, Shriya Atmakuri, Dhruvesh Patel, Xiang Li, and Andrew McCallum

   In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

   Learning representations of words in a continuous space is perhaps the most fundamental task in NLP, however words interact in ways much richer than vector dot product similarity can provide. Many relationships between words can be expressed set-theoretically, for example, adjective-noun compounds (eg. “red cars”⊆“cars”) and homographs (eg. “tongue”∩“body” should be similar to “mouth”, while “tongue”∩“language” should be similar to “dialect”) have natural set-theoretic interpretations. Box embeddings are a novel region-based representation which provide the capability to perform these set-theoretic operations. In this work, we provide a fuzzy-set interpretation of box embeddings, and learn box representations of words using a set-theoretic training objective. We demonstrate improved performance on various word similarity tasks, particularly on less common words, and perform a quantitative and qualitative analysis exploring the additional unique expressivity provided by Word2Box.

7. EMNLP

   Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization

   Nishant Yadav, Nicholas Monath, Rico Angell, Manzil Zaheer, and Andrew McCallum

   In Empirical Methods in Natural Language Processing, 2022
8. EMNLP

   RankGen: Improving Text Generation with Large Ranking Models

   Kalpesh Krishna, Yapei Chang, John Wieting, and Mohit Iyyer

   In Empirical Methods in Natural Language Processing, 2022
9. EMNLP

   Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation

   Tu Vu, Aditya Barua, Brian Lester, Daniel Cer, Mohit Iyyer, and Noah Constant

   In Empirical Methods in Natural Language Processing, 2022
10. EMNLP

    Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature

    Katherine Thai, Marzena Karpinska, Kalpesh Krishna, William Ray, Moira Inghilleri, John Wieting, and Mohit Iyyer

    In Empirical Methods in Natural Language Processing, 2022
11. EMNLP

    SLING: Sino Linguistic Evaluation of Large Language Models

    Yixiao Song, Kalpesh Krishna, Rajesh Bhatt, and Mohit Iyyer

    In Empirical Methods in Natural Language Processing, 2022
12. EMNLP

    DEMETR: Diagnosing Evaluation Metrics for Translation

    Marzena Karpinska, Nishant Raj, Katherine Thai, Yixiao Song, Ankita Gupta, and Mohit Iyyer

    In Empirical Methods in Natural Language Processing, 2022
13. EMNLP-Findings

    You can’t pick your neighbors, or can you? When and How to Rely on Retrieval in the KNN-LM

    Andrew Drozdov, Shufan Wang, Razieh Rahimi, Andrew McCallum, Hamed Zamani, and Mohit Iyyer

    In Empirical Methods in Natural Language Processing, 2022
14. Field Matters

    Corpus-Guided Contrast Sets for Morphosyntactic Feature Detection in Low-Resource English Varieties

    Tessa Masis, Anissa Neal, Lisa Green, and Brendan O’Connor

    In Proceedings of the 1st Field Matters Workshop on NLP Applications to Field Linguistics, 2022
15. ICML

    Knowledge base question answering by case-based reasoning over subgraphs

    Rajarshi Das, Ameya Godbole, Ankita Naik, Elliot Tower, Manzil Zaheer, Hannaneh Hajishirzi, Robin Jia, and Andrew McCallum

    In International Conference on Machine Learning, 2022
16. ICML

    Interactive Correlation Clustering with Existential Cluster Constraints

    Rico Angell, Nicholas Monath, Nishant Yadav, and Andrew McCallum

    In International Conference on Machine Learning, 2022
17. LREC

    Introducing the Gab Hate Corpus: defining and applying hate-based rhetoric to social media posts at scale

    Brendan Kennedy, Mohammad Atari, Aida Mostafazadeh Davani, Leigh Yeh, Ali Omrani, Yehsong Kim, Kris Coombs, Shreya Havaldar, Gwenyth Portillo-Wightman, Elaine Gonzalez, Joe Hoover, Aida Azatian, Alyzeh Hussain, Austin Lara, Gabriel Cardenas, Adam Omary, Christina Park, Xin Wang, Clarisa Wijaya, Yong Zhang, Beth Meyerowitz, and Morteza Dehghani

    In Language Resources and Evaluation, 2022
18. NAACL

    DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions

    Neha Kennard, Tim O’Gorman, Rajarshi Das, Akshay Sharma, Chhandak Bagchi, Matthew Clinton, Pranay Kumar Yelugam, Hamed Zamani, and Andrew McCallum

    In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022

    At the foundation of scientific evaluation is the labor-intensive process of peer review. This critical task requires participants to consume vast amounts of highly technical text. Prior work has annotated different aspects of review argumentation, but discourse relations between reviews and rebuttals have yet to be examined. We present DISAPERE, a labeled dataset of 20k sentences contained in 506 review-rebuttal pairs in English, annotated by experts. DISAPERE synthesizes label sets from prior work and extends them to include fine-grained annotation of the rebuttal sentences, characterizing their context in the review and the authors’ stance towards review arguments. Further, we annotate every review and rebuttal sentence. We show that discourse cues from rebuttals can shed light on the quality and interpretation of reviews. Further, an understanding of the argumentative strategies employed by the reviewers and authors provides useful signal for area chairs and other decision makers.

19. NAACL

    Entity Linking via Explicit Mention-Mention Coreference Modeling

    Dhruv Agarwal, Rico Angell, Nicholas Monath, and Andrew McCallum

    In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022

    Learning representations of entity mentions is a core component of modern entity linking systems for both candidate generation and making linking predictions. In this paper, we present and empirically analyze a novel training approach for learning mention and entity representations that is based on building minimum spanning arborescences (i.e., directed spanning trees) over mentions and entities across documents to explicitly model mention coreference relationships. We demonstrate the efficacy of our approach by showing significant improvements in both candidate generation recall and linking accuracy on the Zero-Shot Entity Linking dataset and MedMentions, the largest publicly available biomedical dataset. In addition, we show that our improvements in candidate generation yield higher quality re-ranking models downstream, setting a new SOTA result in linking accuracy on MedMentions. Finally, we demonstrate that our improved mention representations are also effective for the discovery of new entities via cross-document coreference.

20. NAACL

    Modeling Exemplification in Long-form Question Answering via Retrieval

    Shufan Wang, Fangyuan Xu, Laure Thompson, Eunsol Choi, and Mohit Iyyer

    In North American Association for Computational Linguistics, 2022
21. NAACL

    ChapterBreak: A Challenge Dataset for Long-Range Language Models

    Simeng Sun, Katherine Thai, and Mohit Iyyer

    In North American Association for Computational Linguistics, 2022
22. NLP+CSS

    Examining Political Rhetoric with Epistemic Stance Detection

    Ankita Gupta, Su Lin Blodgett, Justin H Gross, and Brendan O’Connor

    In Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science, 2022
23. Negative Results

    How Much Do Modifications to Transformer Language Models Affect Their Ability to Learn Linguistic Knowledge?

    Simeng Sun, Brian Dillon, and Mohit Iyyer

    In Workshop on Insights from Negative Results in NLP @ ACL 2022, 2022
24. TIIS

    ClioQuery: Interactive Query-Oriented Text Analytics for Comprehensive Investigation of Historical News Archives

    Abram Handler, Narges Mahyar, and Brendan O’Connor

    ACM Trans. Interact. Intell. Syst., 2022

    Historians and archivists often find and analyze the occurrences of query words in newspaper archives to help answer fundamental questions about society. But much work in text analytics focuses on helping people investigate other textual units, such as events, clusters, ranked documents, entity relationships, or thematic hierarchies. Informed by a study into the needs of historians and archivists, we thus propose ClioQuery, a text analytics system uniquely organized around the analysis of query words in context. ClioQuery applies text simplification techniques from natural language processing to help historians quickly and comprehensively gather and analyze all occurrences of a query word across an archive. It also pairs these new NLP methods with more traditional features like linked views and in-text highlighting to help engender trust in summarization techniques. We evaluate ClioQuery with two separate user studies, in which historians explain how ClioQuery’s novel text simplification features can help facilitate historical research. We also evaluate with a separate quantitative comparison study, which shows that ClioQuery helps crowdworkers find and remember historical information. Such results suggest possible new directions for text analytics in other query-oriented settings.

25. W-NUT

    Cross-Dialect Social Media Dependency Parsing for Social Scientific Entity Attribute Analysis

    Chloe Eggleston and Brendan O’Connor

    In Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022), 2022

2021

1. AAAI

   Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications

   Haw-Shiuan Chang, Amol Agrawal, and Andrew McCallum

   In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021

   Paper Bib Poster Slides

   @inproceedings{chang2021extending,
     title = {Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications},
     abbr = {AAAI},
     bibtex_show = {true},
     author = {Chang, Haw-Shiuan and Agrawal, Amol and McCallum, Andrew},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
     year = {2021},
     paper = {https://arxiv.org/abs/2103.15330},
     poster = {https://f6d60bef-de96-4b94-b613-4913f88f2f0f.filesusr.com/ugd/e150d8_3d91e4f3cd6746aeaf24407fc0b674d1.pdf},
     slides = {https://docs.google.com/presentation/d/1k-OBWdBYsGmXUuvNc1_J_JrEppB_Aqh82bJPCgjFL-s/edit?usp=sharing}
   }

2. ACL

   Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models.

   Sumanta Bhattacharyya, Pedram Rooshenas, Subhajit Naskar, Simeng Sun, Mohit Iyyer, and Andrew McCallum

   In Association for Computational Linguistics, 2021

   Paper Bib

   @inproceedings{enmt21,
     abbr = {ACL},
     bibtex_show = {true},
     author = {Bhattacharyya, Sumanta and Rooshenas, Pedram and Naskar, Subhajit and Sun, Simeng and Iyyer, Mohit and McCallum, Andrew},
     booktitle = {Association for Computational Linguistics},
     year = {2021},
     title = {Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models.},
     paper = {https://aclanthology.org/2021.acl-long.349.pdf}
   }

3. ACL Findings

   Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence

   Andrew Halterman, Katherine Keith, Sheikh Sarwar, and Brendan O’Connor

   In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2021
4. Causal NLP

   Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspects

   Katherine Keith, Douglas Rice, and Brendan O’Connor

   In Proceedings of the First Workshop on Causal Inference and NLP, 2021

   Using observed language to understand interpersonal interactions is important in high-stakes decision making. We propose a causal research design for observational (non-experimental) data to estimate the natural direct and indirect effects of social group signals (e.g. race or gender) on speakers’ responses with separate aspects of language as causal mediators. We illustrate the promises and challenges of this framework via a theoretical case study of the effect of an advocate’s gender on interruptions from justices during U.S. Supreme Court oral arguments. We also discuss challenges conceptualizing and operationalizing causal variables such as gender and language that comprise of many components, and we articulate technical open challenges such as temporal dependence between language mediators in conversational settings.

5. EACL

   Changing the Mind of Transformers for Topically-Controllable Language Generation

   Haw-Shiuan Chang, Jiaming Yuan, Mohit Iyyer, and Andrew McCallum

   In Conference of the European Chapter of the Association for Computational Linguistics (EACL) (Oral), 2021

   Paper Bib Code Poster Slides Talk

   @inproceedings{chang2021changing,
     title = {Changing the Mind of Transformers for Topically-Controllable Language Generation},
     abbr = {EACL},
     bibtex_show = {true},
     author = {Chang, Haw-Shiuan and Yuan, Jiaming and Iyyer, Mohit and McCallum, Andrew},
     booktitle = {Conference of the European Chapter of the Association for Computational Linguistics (EACL) (Oral)},
     year = {2021},
     paper = {https://arxiv.org/abs/2103.15335},
     code = {https://github.com/iesl/interactive_LM},
     video = {https://slideslive.com/38954487/changing-the-mind-of-transformers-for-topicallycontrollable-language-generation},
     poster = {https://f6d60bef-de96-4b94-b613-4913f88f2f0f.filesusr.com/ugd/e150d8_87e429adfcb9478e86a55033df144458.pdf},
     slides = {https://f6d60bef-de96-4b94-b613-4913f88f2f0f.filesusr.com/ugd/e150d8_8212c213a26a4c36acc69989aec2399c.key?dn=EACL_interactive_LM.key}
   }

6. EACL

   Multi-facet Universal Schema

   Rohan Paul*, Haw-Shiuan Chang*, and Andrew McCallum

   In Conference of the European Chapter of the Association for Computational Linguistics (EACL) (Oral), 2021

   Paper Bib Code Poster Slides Talk

   @inproceedings{chang2021multi-facet,
     title = {Multi-facet Universal Schema},
     abbr = {EACL},
     bibtex_show = {true},
     author = {Paul*, Rohan and Chang*, Haw-Shiuan and McCallum, Andrew},
     booktitle = {Conference of the European Chapter of the Association for Computational Linguistics (EACL) (Oral)},
     year = {2021},
     paper = {https://arxiv.org/abs/2103.15339},
     code = {https://github.com/rohanpaul11/multifacet-re},
     video = {https://slideslive.com/38954382/multifacet-universal-schema},
     poster = {https://f6d60bef-de96-4b94-b613-4913f88f2f0f.filesusr.com/ugd/e150d8_97d81dbfca604d07b825f2214805166a.pdf},
     slides = {https://f6d60bef-de96-4b94-b613-4913f88f2f0f.filesusr.com/ugd/e150d8_b646fb0d748f43f788131a2dee5e2572.key?dn=EACL_multi-facet_RE_small.key}
   }

7. EMNLP

   Open Aspect Target Sentiment Classification with Natural Language Prompts

   Ronald Seoh, Ian Birle, Mrinal Tak, Haw-Shiuan Chang, Brian Pinette, and Alfred Hough

   In forthcoming EMNLP, 2021
8. EMNLP

   Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP

   Trapit Bansal, Karthick Gunasekaran, Tong Wang, Tsendsuren Munkhdalai, and Andrew McCallum

   In forthcoming EMNLP, 2021
9. EMNLP

   MS-Mentions: Consistently Annotating Entity Mentions in Materials Science Procedural Text

   Tim O’Gorman, Zach Jensen, Sheshera Mysore, Kevin Huang, Rubayyat Mahbub, Elsa Olivetti, and Andrew McCallum

   In forthcoming EMNLP, 2021
10. EMNLP

    Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints

    Zichao Wang, Richard Baraniuk, and Andrew Lan

    In forthcoming EMNLP, 2021
11. EMNLP

    Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration

    Shufan Wang, Laure Thompson, and Mohit Iyyer

    In forthcoming EMNLP, 2021
12. EMNLP

    IGA: An Intent-Guided Authoring Assistant

    Simeng Sun, Wenlong Zhao, Varun Manjunatha, Rajiv Jain, Vlad Morariu, Franck Dernoncourt, Balaji Vasan Srinivasan, and Mohit Iyyer

    In forthcoming EMNLP, 2021
13. EMNLP

    Improved Latent Tree Induction with Distant Supervision via Span Constraints

    Zhiyang Xu, Andrew Drozdov, Jay Yoon Lee, Tim O’Gorman, Subendhu Rongali, Dylan Finkbeiner, Shilpa Suresh, Mohit Iyyer, and Andrew McCallum

    In forthcoming EMNLP, 2021
14. EMNLP

    Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP

    Trapit Bansal, Karthick Prasad Gunasekaran, Tong Wang, Tsendsuren Munkhdalai, and Andrew McCallum

    In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

    Meta-learning considers the problem of learning an efficient learning process that can leverage its past experience to accurately solve new tasks. However, the efficacy of meta-learning crucially depends on the distribution of tasks available for training, and this is often assumed to be known a priori or constructed from limited supervised datasets. In this work, we aim to provide task distributions for meta-learning by considering self-supervised tasks automatically proposed from unlabeled text, to enable large-scale meta-learning in NLP. We design multiple distributions of self-supervised tasks by considering important aspects of task diversity, difficulty, type, domain, and curriculum, and investigate how they affect meta-learning performance. Our analysis shows that all these factors meaningfully alter the task distribution, some inducing significant improvements in downstream few-shot accuracy of the meta-learned models. Empirically, results on 20 downstream tasks show significant improvements in few-shot learning – adding up to +4.2% absolute accuracy (on average) to the previous unsupervised meta-learning method, and perform comparably to supervised methods on the FewRel 2.0 benchmark.

15. EMNLP

    The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation

    Marzena Karpinska, Nader Akoury, and Mohit Iyyer

    In forthcoming EMNLP, 2021
16. EMNLP

    Do Long-Range Language Models Actually Use Long-Range Context?

    Simeng Sun, Kalpesh Krishna, Andrew Mattarella-Micke, and Mohit Iyyer

    In forthcoming EMNLP, 2021
17. EMNLP

    Making Better Use of Unlabeled Data with Task Augmentation and Self-training

    Tu Vu, Thang Luong, Quoc Le, Grady Simon, and Mohit Iyyer

    In forthcoming EMNLP, 2021
18. EMNLP

    Case-based Reasoning for Natural Language Questions over Knowledge Bases

    Rajarshi Das, Manzil Zaheer, Dung Thai, Ameya Godbole, Ethan Perez, Jay-Yoon Lee, Liz Tan, Lazaros Polymenakos, and Andrew McCallum

    In forthcoming EMNLP, 2021
19. EMNLP demo

    Box Embeddings: An open-source library for representation learning using geometric structures

    Tejas Chheda, Purujit Goyal, Trang Tran, Dhruvesh Patel, Michael Boratko, Shib Sankar Dasgupta, and Andrew McCallum

    In forthcoming EMNLP demo, 2021
20. Find. of ACL

    Predicting In-Hospital Mortality by Combining Clinical Notes with Time-Series Data.

    Iman Deznabi, Mohit Iyyer, and Madalina Fiterau

    In Findings of the Association for Computational Linguistics, 2021

    Paper Bib

    @inproceedings{clinical21,
      abbr = {Find. of ACL},
      bibtex_show = {true},
      author = {Deznabi, Iman and Iyyer, Mohit and Fiterau, Madalina},
      booktitle = {Findings of the Association for Computational Linguistics},
      year = {2021},
      title = {Predicting In-Hospital Mortality by Combining Clinical Notes with Time-Series Data.},
      paper = {https://aclanthology.org/2021.findings-acl.352.pdf}
    }

21. Find. of ACL

    Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence

    Andrew Halterman, Katherine Keith, Sheikh Sarwar, and Brendan O’Connor

    In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2021

    Paper Bib

    @inproceedings{halterman-etal-2021-corput,
      bibtex_show = {true},
      abbr = {Find. of ACL},
      paper = {https://aclanthology.org/2021.findings-acl.371.pdf},
      address = {Online},
      author = {Halterman, Andrew and Keith, Katherine and Sarwar, Sheikh and O{'}Connor, Brendan},
      booktitle = {Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021},
      date-added = {2021-08-11 09:39:43 -0400},
      date-modified = {2021-08-11 09:39:43 -0400},
      doi = {10.18653/v1/2021.findings-acl.371},
      month = aug,
      pages = {4240--4253},
      publisher = {Association for Computational Linguistics},
      title = {Corpus-Level Evaluation for Event {QA}: The {I}ndia{P}olice{E}vents Corpus Covering the 2002 {G}ujarat Violence},
      url = {https://aclanthology.org/2021.findings-acl.371},
      year = {2021},
      bdsk-url-1 = {https://aclanthology.org/2021.findings-acl.371},
      bdsk-url-2 = {https://doi.org/10.18653/v1/2021.findings-acl.371}
    }

22. NAACL

    Hurdles to Progress in Long-form Question Answering

    Kalpesh Krishna, Aurko Roy, and Mohit Iyyer

    In North American Association for Computational Linguistics, 2021

    Paper Bib Code

    @inproceedings{lfqa21,
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Krishna, Kalpesh and Roy, Aurko and Iyyer, Mohit},
      booktitle = {North American Association for Computational Linguistics},
      year = {2021},
      title = {Hurdles to Progress in Long-form Question Answering},
      paper = {https://arxiv.org/abs/2103.06332},
      code = {https://github.com/martiansideofthemoon/hurdles-longform-qa}
    }

23. NAACL

    TABBIE: Pretrained Representations of Tabular Data

    Hiroshi Iida, June Thai, Varun Manjunatha, and Mohit Iyyer

    In North American Association for Computational Linguistics, 2021

    Paper Bib Code

    @inproceedings{tabbie21,
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Iida, Hiroshi and Thai, June and Manjunatha, Varun and Iyyer, Mohit},
      booktitle = {North American Association for Computational Linguistics},
      year = {2021},
      title = {TABBIE: Pretrained Representations of Tabular Data},
      paper = {https://arxiv.org/abs/2105.02584},
      code = {https://github.com/SFIG611/tabbie}
    }

24. NAACL

    Revisiting Simple Neural Probabilistic Language Models

    Simeng Sun and Mohit Iyyer

    In North American Association for Computational Linguistics, 2021

    Paper Bib Code

    @inproceedings{stupidlm21,
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Sun, Simeng and Iyyer, Mohit},
      booktitle = {North American Association for Computational Linguistics},
      year = {2021},
      title = {Revisiting Simple Neural Probabilistic Language Models},
      paper = {https://arxiv.org/abs/2104.03474},
      code = {https://github.com/SimengSun/revisit-nplm}
    }

25. NeurIPS

    Capacity and Bias of Learned Geometric Embeddings for Directed Graphs

    Michael Boratko, Dongxu Zhang, Nicholas Monath, Luke Vilnis, Kenneth L Clarkson, and Andrew McCallum

    Advances in Neural Information Processing Systems, 2021
26. UAI

    Min/max stability and box distributions

    Michael Boratko, Javier Burroni, Shib Sankar Dasgupta, and Andrew McCallum

    In Uncertainty in Artificial Intelligence, 2021
27. UAI

    Exact and approximate hierarchical clustering using A

    Craig S Greenberg, Sebastian Macaluso, Nicholas Monath, Avinava Dubey, Patrick Flaherty, Manzil Zaheer, Amr Ahmed, Kyle Cranmer, and Andrew McCallum

    In Uncertainty in Artificial Intelligence, 2021
28. UnImplicit

    Challenges in Detecting Null Relativizers in African American Language for Sociolinguistic and Psycholinguistic Applications

    Anissa Neal, Brendan O’Connor, and Lisa Green

    Unpublished abstract presented at UnImplicit: The First Workshop on Understanding Implicit and Underspecified Language at ACL-IJCNLP, 2021

    Paper Bib

    @conference{Neal2021RC,
      bibtex_show = {true},
      abbr = {UnImplicit},
      paper = {https://people.umass.edu/anneal/files/ACL_IJCNLP_Challenges_in_detecting_null_relativizers_2021.pdf},
      author = {Neal, Anissa and {O'Connor}, Brendan and Green, Lisa},
      info = {Unpublished abstract presented at <i>UnImplicit: The First Workshop on Understanding Implicit and Underspecified Language at ACL-IJCNLP</i>},
      date-added = {2021-08-11 09:41:48 -0400},
      date-modified = {2021-08-11 09:46:18 -0400},
      title = {Challenges in Detecting Null Relativizers in African American Language for Sociolinguistic and Psycholinguistic Applications},
      year = {2021}
    }

2020

1. AAAI

   Simultaneously linking entities and extracting relations from biomedical text without mention-level supervision

   Trapit Bansal, Pat Verga, Neha Choudhary, and Andrew McCallum

   In Proceedings of the AAAI Conference on Artificial Intelligence, 2020

   Bib

   @inproceedings{bansal2020simultaneously,
     title = {Simultaneously linking entities and extracting relations from biomedical text without mention-level supervision},
     abbr = {AAAI},
     bibtex_show = {true},
     author = {Bansal, Trapit and Verga, Pat and Choudhary, Neha and McCallum, Andrew},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
     volume = {34},
     number = {05},
     pages = {7407--7414},
     year = {2020}
   }

2. ACL

   Hard-Coded Gaussian Attention for Neural Machine Translation

   Weiqiu You, Simeng Sun, and Mohit Iyyer

   In Association for Computational Linguistics, 2020

   Paper Bib Code

   @inproceedings{acl2020,
     abbr = {ACL},
     bibtex_show = {true},
     author = {You, Weiqiu and Sun, Simeng and Iyyer, Mohit},
     booktitle = {Association for Computational Linguistics},
     year = {2020},
     title = {Hard-Coded Gaussian Attention for Neural Machine Translation},
     paper = {https://arxiv.org/abs/2005.00742},
     code = {https://github.com/fallcat/stupidNMT}
   }

3. ACL

   Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates

   Katherine Keith, David Jensen, and Brendan O’Connor

   In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020

   Paper Bib

   Many applications of computational social science aim to infer causal conclusions from non-experimental data. Such observational data often contains confounders, variables that influence both potential causes and potential effects. Unmeasured or latent confounders can bias causal estimates, and this has motivated interest in measuring potential confounders from observed text. For example, an individual’s entire history of social media posts or the content of a news article could provide a rich measurement of multiple confounders.Yet, methods and applications for this problem are scattered across different communities and evaluation practices are inconsistent.This review is the first to gather and categorize these examples and provide a guide to data-processing and evaluation decisions. Despite increased attention on adjusting for confounding using text, there are still many open problems, which we highlight in this paper.

   @inproceedings{keith-etal-2020-text,
     bibtex_show = {true},
     abbr = {ACL},
     paper = {https://aclanthology.org/2020.acl-main.474.pdf},
     address = {Online},
     author = {Keith, Katherine and Jensen, David and O{'}Connor, Brendan},
     booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
     date-added = {2021-08-11 09:45:48 -0400},
     date-modified = {2021-08-11 09:45:48 -0400},
     doi = {10.18653/v1/2020.acl-main.474},
     month = jul,
     pages = {5332--5344},
     publisher = {Association for Computational Linguistics},
     title = {Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates},
     url = {https://aclanthology.org/2020.acl-main.474},
     year = {2020},
     bdsk-url-1 = {https://aclanthology.org/2020.acl-main.474},
     bdsk-url-2 = {https://doi.org/10.18653/v1/2020.acl-main.474}
   }

4. CLEF

   Unsupervised Pre-training for Biomedical Question Answering

   Vaishnavi Kommaraju, Karthick Gunasekaran, Kun Li, Trapit Bansal, Andrew McCallum, Ivana Williams, and Ana-Maria Istrate

   In CLEF (Working Notes), 2020

   Paper Bib

   @inproceedings{DBLP:conf/clef/KommarajuGLBMWI20,
     abbr = {CLEF},
     bibtex_show = {true},
     author = {Kommaraju, Vaishnavi and Gunasekaran, Karthick and Li, Kun and Bansal, Trapit and McCallum, Andrew and Williams, Ivana and Istrate, Ana-Maria},
     title = {Unsupervised Pre-training for Biomedical Question Answering},
     year = {2020},
     cdate = {1577836800000},
     paper = {http://ceur-ws.org/Vol-2696/paper_144.pdf},
     booktitle = {CLEF (Working Notes)},
     crossref = {conf/clef/2020w}
   }

5. COLING

   Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks

   Trapit Bansal, Rishikesh Jha, and Andrew McCallum

   In Proceedings of the 28th International Conference on Computational Linguistics, 2020

   Bib

   @inproceedings{bansal2020learning,
     title = {Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks},
     abbr = {COLING},
     bibtex_show = {true},
     author = {Bansal, Trapit and Jha, Rishikesh and McCallum, Andrew},
     booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
     pages = {5108--5123},
     year = {2020}
   }

6. ECIR

   Weakly-Supervised Open-Retrieval Conversational Question Answering

   Chen Qu, Liu Yang, Cen Chen, W. Bruce Croft, Kalpesh Krishna, and Mohit Iyyer

   In European Conference on Information Retrieval, 2020

   Paper Bib

   @inproceedings{ecir20,
     abbr = {ECIR},
     bibtex_show = {true},
     author = {Qu, Chen and Yang, Liu and Chen, Cen and Croft, W. Bruce and Krishna, Kalpesh and Iyyer, Mohit},
     booktitle = {European Conference on Information Retrieval},
     year = {2020},
     title = {Weakly-Supervised Open-Retrieval Conversational Question Answering},
     paper = {https://arxiv.org/abs/2103.02537}
   }

7. EMNLP

   Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks

   Trapit Bansal, Rishikesh Jha, Tsendsuren Munkhdalai, and Andrew McCallum

   In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020

   Bib

   @inproceedings{bansal2020self,
     title = {Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks},
     abbr = {EMNLP},
     bibtex_show = {true},
     author = {Bansal, Trapit and Jha, Rishikesh and Munkhdalai, Tsendsuren and McCallum, Andrew},
     booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
     pages = {522--534},
     year = {2020}
   }

8. EMNLP

   Exploring and Predicting Transferability across NLP Tasks

   Tu Vu, Tong Wang, Tsendsuren Munkhdalai, Alessandro Sordoni, Adam Trischler, Andrew Mattarella-Micke, Subhransu Maji, and Mohit Iyyer

   In Empirical Methods in Natural Language Processing, 2020

   Paper Bib Code

   @inproceedings{transfer20,
     abbr = {EMNLP},
     bibtex_show = {true},
     author = {Vu, Tu and Wang, Tong and Munkhdalai, Tsendsuren and Sordoni, Alessandro and Trischler, Adam and Mattarella-Micke, Andrew and Maji, Subhransu and Iyyer, Mohit},
     booktitle = {Empirical Methods in Natural Language Processing},
     year = {2020},
     title = {Exploring and Predicting Transferability across NLP Tasks},
     paper = {https://arxiv.org/abs/2005.00770},
     code = {https://github.com/tuvuumass/task-transferability}
   }

9. EMNLP

   Reformulating Unsupervised Style Transfer as Paraphrase Generation

   Kalpesh Krishna, John Wieting, and Mohit Iyyer

   In Empirical Methods in Natural Language Processing, 2020

   Paper Bib Code

   @inproceedings{style20,
     abbr = {EMNLP},
     bibtex_show = {true},
     author = {Krishna, Kalpesh and Wieting, John and Iyyer, Mohit},
     booktitle = {Empirical Methods in Natural Language Processing},
     year = {2020},
     title = {Reformulating Unsupervised Style Transfer as Paraphrase Generation},
     paper = {https://arxiv.org/abs/2010.05700},
     code = {http://style.cs.umass.edu/}
   }

10. EMNLP

    STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation

    Nader Akoury, Shufan Wang, Josh Whiting, Stephen Hood, Nanyun Peng, and Mohit Iyyer

    In Empirical Methods in Natural Language Processing, 2020

    Paper Bib Code

    @inproceedings{storium20,
      abbr = {EMNLP},
      bibtex_show = {true},
      author = {Akoury, Nader and Wang, Shufan and Whiting, Josh and Hood, Stephen and Peng, Nanyun and Iyyer, Mohit},
      booktitle = {Empirical Methods in Natural Language Processing},
      year = {2020},
      title = {STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation},
      paper = {https://arxiv.org/abs/2010.01717},
      code = {https://storium.cs.umass.edu/}
    }

11. EMNLP

    Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders

    Andrew Drozdov, Subendhu Rongali, Yi-Pei Chen, Tim O’Gorman, Mohit Iyyer, and Andrew McCallum

    In Empirical Methods in Natural Language Processing, 2020

    Paper Bib

    @inproceedings{sdiora20,
      abbr = {EMNLP},
      bibtex_show = {true},
      author = {Drozdov, Andrew and Rongali, Subendhu and Chen, Yi-Pei and O'Gorman, Tim and Iyyer, Mohit and McCallum, Andrew},
      booktitle = {Empirical Methods in Natural Language Processing},
      year = {2020},
      title = {Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders},
      paper = {https://mrdrozdov.github.io/static/papers/sdiora.pdf}
    }

12. ICLR

    Thieves on Sesame Street! Model Extraction of BERT-based APIs.

    Kalpesh Krishna, Gaurav Singh Tomar, Ankur Parikh, Nicolas Papernot, and Mohit Iyyer

    In International Conference on Learning Representations, 2020

    Paper Bib Code

    @inproceedings{thieves20,
      abbr = {ICLR},
      bibtex_show = {true},
      author = {Krishna, Kalpesh and Tomar, Gaurav Singh and Parikh, Ankur and Papernot, Nicolas and Iyyer, Mohit},
      booktitle = {International Conference on Learning Representations},
      year = {2020},
      title = {Thieves on Sesame Street! Model Extraction of BERT-based APIs.},
      paper = {https://arxiv.org/abs/1910.12366},
      code = {https://github.com/google-research/language/tree/master/language/bert_extraction}
    }

13. LREC

    Which Evaluations Uncover Sense Representations that Actually Make Sense?

    Fenfei Guo, Jordan Boyd-Graber, Mohit Iyyer, and Leah Findlater

    In Language Resources and Evaluation Conference, 2020

    Paper Bib

    @inproceedings{lrec2020,
      abbr = {LREC},
      bibtex_show = {true},
      author = {Guo, Fenfei and Boyd-Graber, Jordan and Iyyer, Mohit and Findlater, Leah},
      booktitle = {Language Resources and Evaluation Conference},
      year = {2020},
      title = {Which Evaluations Uncover Sense Representations that Actually Make Sense?},
      paper = {https://arxiv.org/abs/1804.08077}
    }

14. ML

    Using Error Decay Prediction to Overcome Practical Issues of Deep Active Learning for Named Entity Recognition

    Haw-Shiuan Chang, Shankar Vembu, Sunil Mohan, Rheeya Uppaal, and Andrew McCallum

    Machine Learning, 2020

    Paper Bib Slides Talk

    @article{chang2019ovecoming,
      abbr = {ML},
      bibtex_show = {true},
      author = {Chang, Haw-Shiuan and Vembu, Shankar and Mohan, Sunil and Uppaal, Rheeya and McCallum, Andrew},
      journal = {Machine Learning},
      paper = {http://arxiv.org/abs/1911.07335},
      title = {Using Error Decay Prediction to Overcome Practical Issues of Deep Active Learning for Named Entity Recognition},
      year = {2020},
      doi = {10.1007/s10994-020-05897-1},
      publisher = {Springer},
      video = {https://slideslive.com/38933012/using-error-decay-prediction-to-overcome-practical-issues-of-deep-active-learning-for-named-entity-recognition},
      slides = {https://docs.google.com/presentation/d/1h3bI1dS8-vS5ItcfGOHN3J7Wi7dnWWBf0gA4-yBXrk4/edit?usp=sharing}
    }

15. NLP+CSS

    Analyzing Gender Bias within Narrative Tropes

    Dhruvil Gala, Mohammad Omar Khursheed, Hannah Lerner, Brendan O’Connor, and Mohit Iyyer

    In Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science, 2020

    Paper Bib Code

    @inproceedings{tropes20,
      abbr = {NLP+CSS},
      bibtex_show = {true},
      author = {Gala, Dhruvil and Khursheed, Mohammad Omar and Lerner, Hannah and O'Connor, Brendan and Iyyer, Mohit},
      booktitle = {Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science},
      year = {2020},
      title = {Analyzing Gender Bias within Narrative Tropes},
      paper = {https://aclanthology.org/2020.nlpcss-1.23.pdf},
      code = {https://github.com/dhruvilgala/tvtropes}
    }

16. NLP+CSS

    Uncertainty over Uncertainty: Investigating the Assumptions, Annotations, and Text Measurements of Economic Policy Uncertainty

    Katherine Keith, Christoph Teichmann, Brendan O’Connor, and Edgar Meij

    In Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science, 2020

    Paper Bib

    Methods and applications are inextricably linked in science, and in particular in the domain of text-as-data. In this paper, we examine one such text-as-data application, an established economic index that measures economic policy uncertainty from keyword occurrences in news. This index, which is shown to correlate with firm investment, employment, and excess market returns, has had substantive impact in both the private sector and academia. Yet, as we revisit and extend the original authors’ annotations and text measurements we find interesting text-as-data methodological research questions: (1) Are annotator disagreements a reflection of ambiguity in language? (2) Do alternative text measurements correlate with one another and with measures of external predictive validity? We find for this application (1) some annotator disagreements of economic policy uncertainty can be attributed to ambiguity in language, and (2) switching measurements from keyword-matching to supervised machine learning classifiers results in low correlation, a concerning implication for the validity of the index.

    @inproceedings{keith-etal-2020-uncertainty,
      bibtex_show = {true},
      abbr = {NLP+CSS},
      paper = {https://aclanthology.org/2020.nlpcss-1.13.pdf},
      address = {Online},
      author = {Keith, Katherine and Teichmann, Christoph and O{'}Connor, Brendan and Meij, Edgar},
      booktitle = {Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science},
      date-added = {2021-08-11 09:45:36 -0400},
      date-modified = {2021-08-11 09:45:36 -0400},
      doi = {10.18653/v1/2020.nlpcss-1.13},
      month = nov,
      pages = {116--131},
      publisher = {Association for Computational Linguistics},
      title = {Uncertainty over Uncertainty: Investigating the Assumptions, Annotations, and Text Measurements of Economic Policy Uncertainty},
      url = {https://aclanthology.org/2020.nlpcss-1.13},
      year = {2020},
      bdsk-url-1 = {https://aclanthology.org/2020.nlpcss-1.13},
      bdsk-url-2 = {https://doi.org/10.18653/v1/2020.nlpcss-1.13}
    }

17. SIGIR

    Open-Retrieval Conversational Question Answering

    Chen Qu, Liu Yang, Cen Chen, Minghui Qiu, W. Bruce Croft, and Mohit Iyyer

    In 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020

    Paper Bib

    @inproceedings{openconvqa,
      abbr = {SIGIR},
      bibtex_show = {true},
      author = {Qu, Chen and Yang, Liu and Chen, Cen and Qiu, Minghui and Croft, W. Bruce and Iyyer, Mohit},
      booktitle = {43rd International ACM SIGIR Conference on Research and Development in Information Retrieval},
      year = {2020},
      title = {Open-Retrieval Conversational Question Answering},
      paper = {https://arxiv.org/abs/2005.11364}
    }

18. Sci. Adv.

    Elusive Consensus: Polarization in Elite Communication on the COVID-19 Pandemic

    Jon Greene, Jared Edgerton, Daniel Naftel, Kelsey Shoub, and Skyler Cranmer

    Science Advances, 2020
19. arXiv

    Topic Modeling with Contextualized Word Representation Clusters

    Laure Thompson and David Mimno

    arXiv preprint arXiv:2010.12626, 2020

    Paper Bib

    @article{thompson2020topic,
      abbr = {arXiv},
      bibtex_show = {true},
      paper = {https://arxiv.org/pdf/2010.12626.pdf},
      title = {Topic Modeling with Contextualized Word Representation Clusters},
      author = {Thompson, Laure and Mimno, David},
      year = {2020},
      journal = {arXiv preprint arXiv:2010.12626}
    }

2019

1. ACL

   Optimal Transport-based Alignment of Learned Character Representations for String Similarity

   Derek Tam, Nicholas Monath, Ari Kobren, Aaron Traylor, Rajarshi Das, and Andrew McCallum

   In Association of Computational Linguistics (ACL), 2019

   Bib

   @inproceedings{tam2019optimal,
     title = {Optimal Transport-based Alignment of Learned Character Representations for String Similarity},
     abbr = {ACL},
     bibtex_show = {true},
     author = {Tam, Derek and Monath, Nicholas and Kobren, Ari and Traylor, Aaron and Das, Rajarshi and McCallum, Andrew},
     booktitle = {Association of Computational Linguistics (ACL)},
     year = {2019}
   }

2. ACL

   A2N: Attending to Neighbors for Knowledge Graph Inference

   Trapit Bansal, Da-Cheng Juan, Sujith Ravi, and Andrew McCallum

   In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019

   Paper Bib

   @inproceedings{bansal-etal-2019-a2n,
     title = {{A}2{N}: Attending to Neighbors for Knowledge Graph Inference},
     abbr = {ACL},
     bibtex_show = {true},
     author = {Bansal, Trapit and Juan, Da-Cheng and Ravi, Sujith and McCallum, Andrew},
     booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
     month = jul,
     year = {2019},
     address = {Florence, Italy},
     publisher = {Association for Computational Linguistics},
     paper = {https://www.aclweb.org/anthology/P19-1431},
     doi = {10.18653/v1/P19-1431},
     pages = {4387--4392}
   }

3. ACL

   Syntactically Supervised Transformers for Faster Neural Machine Translation

   Nader Akoury, Kalpesh Krishna, and Mohit Iyyer

   In Association for Computational Linguistics, 2019

   Paper Bib Code

   @inproceedings{synst2019,
     abbr = {ACL},
     bibtex_show = {true},
     author = {Akoury, Nader and Krishna, Kalpesh and Iyyer, Mohit},
     booktitle = {Association for Computational Linguistics},
     year = {2019},
     title = {Syntactically Supervised Transformers for Faster Neural Machine Translation},
     paper = {https://arxiv.org/abs/1906.02780},
     code = {https://github.com/dojoteef/synst}
   }

4. ACL

   Generating Question-Answer Hierarchies

   Kalpesh Krishna and Mohit Iyyer

   In Association for Computational Linguistics, 2019

   Paper Bib Code

   @inproceedings{squash2019,
     abbr = {ACL},
     bibtex_show = {true},
     author = {Krishna, Kalpesh and Iyyer, Mohit},
     booktitle = {Association for Computational Linguistics},
     year = {2019},
     title = {Generating Question-Answer Hierarchies},
     paper = {https://arxiv.org/abs/1906.02622},
     code = {http://squash.cs.umass.edu/}
   }

5. ACL

   Encouraging Paragraph Embeddings to Remember Sentence Identity Improves Classification

   Tu Vu and Mohit Iyyer

   In Association for Computational Linguistics, 2019

   Paper Bib Code

   @inproceedings{paraemb2019,
     abbr = {ACL},
     bibtex_show = {true},
     author = {Vu, Tu and Iyyer, Mohit},
     booktitle = {Association for Computational Linguistics},
     year = {2019},
     title = {Encouraging Paragraph Embeddings to Remember Sentence Identity Improves Classification},
     paper = {https://arxiv.org/abs/1906.03656},
     code = {https://github.com/tuvuumass/SCoPE}
   }

6. AKBC

   Integrating User Feedback under Identity Uncertainty in Knowledge Base Construction

   Ari Kobren, Nicholas Monath, and Andrew McCallum

   In Automated Knowledge Base Construction (AKBC), 2019

   Paper Bib

   @inproceedings{kobren2019feedback,
     title = {Integrating User Feedback under Identity Uncertainty in Knowledge Base Construction},
     abbr = {AKBC},
     bibtex_show = {true},
     author = {Kobren, Ari and Monath, Nicholas and McCallum, Andrew},
     booktitle = {Automated Knowledge Base Construction (AKBC)},
     year = {2019},
     paper = {https://openreview.net/forum?id=SygLHbcapm}
   }

7. CIKM

   Attentive History Selection for Conversational Question Answering

   Chen Qu, Liu Yang, Minghui Qiu, Yongfeng Zhang, Cen Chen, W. Bruce Croft, and Mohit Iyyer

   In Conference on Information and Knowledge Management, 2019

   Paper Bib

   @inproceedings{cikm2019,
     abbr = {CIKM},
     bibtex_show = {true},
     author = {Qu, Chen and Yang, Liu and Qiu, Minghui and Zhang, Yongfeng and Chen, Cen and Croft, W. Bruce and Iyyer, Mohit},
     booktitle = {Conference on Information and Knowledge Management},
     year = {2019},
     title = {Attentive History Selection for Conversational Question Answering},
     paper = {https://arxiv.org/abs/1908.09456}
   }

8. EMNLP

   Query-focused Sentence Compression in Linear Time

   Abram Handler and Brendan O’Connor

   In Proceedings of EMNLP, 2019

   Paper Bib

   @inproceedings{Handler2019Compression,
     bibtex_show = {true},
     abbr = {EMNLP},
     paper = {https://aclanthology.org/D19-1612.pdf},
     author = {Handler, Abram and O'Connor, Brendan},
     booktitle = {Proceedings of {EMNLP}},
     date-added = {2019-09-03 01:25:49 +0000},
     date-modified = {2019-09-03 01:26:13 +0000},
     title = {Query-focused Sentence Compression in Linear Time},
     year = {2019}
   }

9. EMNLP

   Investigating Sports Commentator Bias within a Large Corpus of American Football Broadcasts.

   Jack Merullo, Luke Yeh, Abram Handler, Alvin Grissom II, Brendan O’Connor, and Mohit Iyyer

   In Empirical Methods in Natural Language Processing, 2019

   Paper Bib Code

   @inproceedings{football2019,
     abbr = {EMNLP},
     bibtex_show = {true},
     author = {Merullo, Jack and Yeh, Luke and Handler, Abram and II, Alvin Grissom and O'Connor, Brendan and Iyyer, Mohit},
     booktitle = {Empirical Methods in Natural Language Processing},
     year = {2019},
     title = {Investigating Sports Commentator Bias within a Large Corpus of American Football Broadcasts.},
     paper = {https://arxiv.org/abs/1909.03343},
     code = {https://github.com/jmerullo/football}
   }

10. EMNLP

    Unsupervised Labeled Parsing with Deep Inside-Outside Recursive Autoencoders

    Andrew Drozdov, Patrick Verga, Yi-Pei Chen, Mohit Iyyer, and Andrew McCallum

    In Empirical Methods in Natural Language Processing, 2019

    Paper Bib

    @inproceedings{diora2_2019,
      abbr = {EMNLP},
      bibtex_show = {true},
      author = {Drozdov, Andrew and Verga, Patrick and Chen, Yi-Pei and Iyyer, Mohit and McCallum, Andrew},
      booktitle = {Empirical Methods in Natural Language Processing},
      year = {2019},
      title = {Unsupervised Labeled Parsing with Deep Inside-Outside Recursive Autoencoders},
      paper = {https://www.aclweb.org/anthology/D19-1161.pdf}
    }

11. ICLR

    Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering

    Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, and Andrew McCallum

    In International Conference on Learning Representations (ICLR), 2019

    Paper Bib

    @inproceedings{das2019multi-step,
      title = {Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering},
      abbr = {ICLR},
      bibtex_show = {true},
      author = {Das, Rajarshi and Dhuliawala, Shehzaad and Zaheer, Manzil and McCallum, Andrew},
      booktitle = {International Conference on Learning Representations (ICLR)},
      year = {2019},
      paper = {https://openreview.net/forum?id=HkfPSh05K7}
    }

12. ICLR

    Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension

    Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, and Andrew McCallum

    In International Conference on Learning Representations (ICLR), 2019

    Paper Bib

    @inproceedings{das2019building,
      title = {Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension},
      abbr = {ICLR},
      bibtex_show = {true},
      author = {Das, Rajarshi and Dhuliawala, Shehzaad and Zaheer, Manzil and McCallum, Andrew},
      booktitle = {International Conference on Learning Representations (ICLR)},
      year = {2019},
      paper = {https://openreview.net/forum?id=S1lhbnRqF7}
    }

13. ICLR

    Smoothing the Geometry of Box Embeddings

    Xiang Li, Luke Vilnis, Dongxu Zhang, Michael Boratko, and Andrew McCallum

    In International Conference on Learning Representations (ICLR) (Oral), 2019

    Paper Bib

    @inproceedings{li2019smoothing,
      title = {Smoothing the Geometry of Box Embeddings},
      abbr = {ICLR},
      bibtex_show = {true},
      author = {Li, Xiang and Vilnis, Luke and Zhang, Dongxu and Boratko, Michael and McCallum, Andrew},
      booktitle = {International Conference on Learning Representations (ICLR) (Oral)},
      year = {2019},
      paper = {https://openreview.net/forum?id=H1xSNiRcF7}
    }

14. ICML

    Supervised Hierarchical Clustering with Exponential Linkage

    Nishant Yadav, Ari Kobren, Nicholas Monath, and Andrew McCallum

    In International Conference on Machine Learning (ICML), 2019

    Paper Bib Code

    @inproceedings{yadav2019supervised,
      title = {Supervised Hierarchical Clustering with Exponential Linkage},
      abbr = {ICML},
      bibtex_show = {true},
      author = {Yadav, Nishant and Kobren, Ari and Monath, Nicholas and McCallum, Andrew},
      booktitle = {International Conference on Machine Learning (ICML)},
      year = {2019},
      paper = {http://proceedings.mlr.press/v97/yadav19a/yadav19a.pdf},
      code = {https://github.com/iesl/expLinkage}
    }

15. JLC

    Measuring the Issue Content of Supreme Court Opinions

    Douglas Rice

    Journal of Law and Courts, 2019
16. KDD

    Gradient-based Hierarchical Clustering using Continuous Representations of Trees in Hyperbolic Space

    Nicholas Monath, Manzil Zaheer, Daniel Silva, Andrew McCallum, and Amr Ahmed

    In International Conference on Knowledge Discovery and Data Mining (KDD), 2019

    Bib

    @inproceedings{monath2019gradient,
      title = {Gradient-based Hierarchical Clustering using Continuous Representations of Trees in Hyperbolic Space},
      abbr = {KDD},
      bibtex_show = {true},
      author = {Monath, Nicholas and Zaheer, Manzil and Silva, Daniel and McCallum, Andrew and Ahmed, Amr},
      booktitle = {International Conference on Knowledge Discovery and Data Mining (KDD)},
      year = {2019}
    }

17. KDD

    Paper Matching with Local Fairness Constraints

    Ari Kobren, Barna Saha, and Andrew McCallum

    In International Conference on Knowledge Discovery and Data Mining (KDD), 2019

    Paper Bib Code

    @inproceedings{kobren2019matching,
      title = {Paper Matching with Local Fairness Constraints},
      abbr = {KDD},
      bibtex_show = {true},
      author = {Kobren, Ari and Saha, Barna and McCallum, Andrew},
      booktitle = {International Conference on Knowledge Discovery and Data Mining (KDD)},
      year = {2019},
      code = {https://github.com/iesl/fair-matching},
      paper = {https://arxiv.org/abs/1905.11924}
    }

18. KDD

    Scalable Hierarchical Clustering with Tree Grafting

    Nicholas Monath, Ari Kobren, Akshay Krishnamurthy, Michael Glass, and Andrew McCallum

    In International Conference on Knowledge Discovery and Data Mining (KDD), 2019

    Bib

    @inproceedings{monath2019grinch,
      title = {Scalable Hierarchical Clustering with Tree Grafting},
      abbr = {KDD},
      bibtex_show = {true},
      author = {Monath, Nicholas and Kobren, Ari and Krishnamurthy, Akshay and Glass, Michael and McCallum, Andrew},
      booktitle = {International Conference on Knowledge Discovery and Data Mining (KDD)},
      year = {2019}
    }

19. LA+ACL

    The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures

    Sheshera Mysore, Zach Jensen, Edward Kim, Kevin Huang, Haw-Shiuan Chang, Emma Strubell, Jeffrey Flanigan, Andrew McCallum, and Elsa Olivetti

    In Proceedings of the 13th Linguistic Annotation Workshop at ACL, 2019

    Paper Bib

    @inproceedings{mysore2019msannlaw,
      title = {The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures},
      abbr = {LA+ACL},
      bibtex_show = {true},
      author = {Mysore, Sheshera and Jensen, Zach and Kim, Edward and Huang, Kevin and Chang, Haw-Shiuan and Strubell, Emma and Flanigan, Jeffrey and McCallum, Andrew and Olivetti, Elsa},
      booktitle = {Proceedings of the 13th Linguistic Annotation Workshop at ACL},
      year = {2019},
      paper = {https://sigann.github.io/LAW-XIII-2019/pdf/W19-4007.pdf}
    }

20. NAACL

    Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders

    Andrew Drozdov, Patrick Verga, Mohit Yadav, Mohit Iyyer, and Andrew McCallum

    In North American Association for Computational Linguistics, 2019

    Paper Bib Code

    @inproceedings{DIORA2019,
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Drozdov, Andrew and Verga, Patrick and Yadav, Mohit and Iyyer, Mohit and McCallum, Andrew},
      booktitle = {North American Association for Computational Linguistics},
      year = {2019},
      title = {Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders},
      paper = {https://arxiv.org/abs/1904.02142},
      code = {https://github.com/iesl/diora}
    }

21. NAACL

    Casting Light on Invisible Cities: Computationally Engaging with Literary Criticism

    Shufan Wang and Mohit Iyyer

    In North American Association for Computational Linguistics, 2019

    Paper Bib

    @inproceedings{Wang2019,
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Wang, Shufan and Iyyer, Mohit},
      booktitle = {North American Association for Computational Linguistics},
      year = {2019},
      title = {Casting Light on Invisible Cities: Computationally Engaging with Literary Criticism},
      paper = {https://arxiv.org/abs/1904.08386}
    }

22. NAACL

    OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference

    Dongxu Zhang, Subhabrata Mukherjee, Colin Lockard, Luna Dong, and Andrew McCallum

    In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), 2019

    Paper Bib

    @inproceedings{zhang2019openki,
      title = {OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference},
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Zhang, Dongxu and Mukherjee, Subhabrata and Lockard, Colin and Dong, Luna and McCallum, Andrew},
      booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)},
      pages = {762--772},
      year = {2019},
      paper = {https://www.aclweb.org/anthology/N19-1083}
    }

23. SCiL

    Preface: SCiL 2019 Editors’ Note

    Gaja Jarosz, Max Nelson, Brendan O’Connor, and Joe Pater

    Proceedings of the Society for Computation in Linguistics, 2019

    Paper Bib

    @article{Jarosz2019SCiL,
      bibtex_show = {true},
      abbr = {SCiL},
      paper = {https://doi.org/10.7275/ntf6-xx21},
      author = {Jarosz, Gaja and Nelson, Max and O'Connor, Brendan and Pater, Joe},
      date-added = {2019-09-03 01:37:37 +0000},
      date-modified = {2021-08-11 10:08:08 -0400},
      journal = {Proceedings of the Society for Computation in Linguistics},
      number = {1},
      title = {Preface: {SCiL} 2019 Editors' Note},
      volume = {2},
      year = {2019}
    }

24. SIGIR

    BERT with History Modeling for Conversational Question Answering

    Chen Qu, Liu Yang, Minghui Qiu, W. Bruce Croft, Yongfeng Zhang, and Mohit Iyyer

    In 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019

    Paper Bib Code

    @inproceedings{ConvQA2019,
      abbr = {SIGIR},
      bibtex_show = {true},
      author = {Qu, Chen and Yang, Liu and Qiu, Minghui and Croft, W. Bruce and Zhang, Yongfeng and Iyyer, Mohit},
      booktitle = {42nd International ACM SIGIR Conference on Research and Development in Information Retrieval},
      year = {2019},
      title = {BERT with History Modeling for Conversational Question Answering},
      paper = {https://arxiv.org/abs/1905.05412},
      code = {https://github.com/prdwb/bert_hae}
    }

25. arXiv

    Human acceptability judgements for extractive sentence compression

    Abram Handler, Brian Dillon, and Brendan O’Connor

    arXiv preprint arXiv:1902.00489, 2019

    Paper Bib

    @article{Handler2019Human,
      bibtex_show = {true},
      abbr = {arXiv},
      paper = {https://arxiv.org/pdf/1902.00489.pdf},
      author = {Handler, Abram and Dillon, Brian and O'Connor, Brendan},
      date-added = {2019-09-05 04:46:18 +0000},
      date-modified = {2019-09-05 04:46:24 +0000},
      journal = {arXiv preprint arXiv:1902.00489},
      title = {Human acceptability judgements for extractive sentence compression},
      year = {2019}
    }

2018

1. ACL

   Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures

   Luke Vilnis*, Xiang Li*, Shikhar Murty, and Andrew McCallum (* Equal Contribution)

   In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), 2018

   Paper Bib

   @inproceedings{DBLP:conf/acl/Vilnis18,
     abbr = {ACL},
     bibtex_show = {true},
     author = {Vilnis*, Luke and Li*, Xiang and Murty, Shikhar and indicates Equal Contribution), Andrew McCallum (*},
     title = {Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures},
     booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL)},
     year = {2018},
     paper = {http://people.cs.umass.edu/~luke/box-lattices.pdf}
   }

2. ACL

   Twitter Universal Dependency Parsing for African-American and Mainstream American English

   Su Lin Blodgett, Johnny Wei, and Brendan O’Connor

   In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018

   Paper Bib

   Due to the presence of both Twitter-specific conventions and non-standard and dialectal language, Twitter presents a significant parsing challenge to current dependency parsing tools. We broaden English dependency parsing to handle social media English, particularly social media African-American English (AAE), by developing and annotating a new dataset of 500 tweets, 250 of which are in AAE, within the Universal Dependencies 2.0 framework. We describe our standards for handling Twitter- and AAE-specific features and evaluate a variety of cross-domain strategies for improving parsing with no, or very little, in-domain labeled data, including a new data synthesis approach. We analyze these methods’ impact on performance disparities between AAE and Mainstream American English tweets, and assess parsing accuracy for specific AAE lexical and syntactic features. Our annotated data and a parsing model are available at: http://slanglab.cs.umass.edu/TwitterAAE/.

   @inproceedings{Blodgett2018Parsing,
     bibtex_show = {true},
     abbr = {ACL},
     paper = {http://www.aclweb.org/anthology/P18-1131.pdf},
     address = {Melbourne, Australia},
     author = {Blodgett, Su Lin and Wei, Johnny and O'Connor, Brendan},
     booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
     date-added = {2018-07-18 07:19:10 +0000},
     date-modified = {2018-07-18 11:55:28 +0000},
     month = jul,
     pages = {1415--1425},
     publisher = {Association for Computational Linguistics},
     title = {{Twitter Universal Dependency} Parsing for {African-American} and Mainstream {American English}},
     url = {http://www.aclweb.org/anthology/P18-1131},
     year = {2018},
     bdsk-url-1 = {http://www.aclweb.org/anthology/P18-1131}
   }

3. ACL

   Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking

   Shikhar Murty*, Patrick Verga*, Luke Vilnis, Irena Radovanovic, and Andrew McCallum (* Equal Contribution)

   In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL) (Oral), 2018

   Paper Bib

   @inproceedings{DBLP:conf/acl/Murty18,
     abbr = {ACL},
     bibtex_show = {true},
     author = {Murty*, Shikhar and Verga*, Patrick and Vilnis, Luke and Radovanovic, Irena and indicates Equal Contribution), Andrew McCallum (*},
     title = {Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking},
     booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL) (Oral)},
     year = {2018},
     paper = {http://aclweb.org/anthology/P18-1010}
   }

4. BlackboxNLP

   Evaluating Grammaticality in Seq2seq Models with a Broad Coverage HPSG Grammar: A Case Study on Machine Translation

   Johnny Wei, Khiem Pham, Brendan O’Connor, and Brian Dillon

   In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 2018

   Paper Bib

   Sequence to sequence (seq2seq) models are often employed in settings where the target output is natural language. However, the syntactic properties of the language generated from these models are not well understood. We explore whether such output belongs to a formal and realistic grammar, by employing the English Resource Grammar (ERG), a broad coverage, linguistically precise HPSG-based grammar of English. From a French to English parallel corpus, we analyze the parseability and grammatical constructions occurring in output from a seq2seq translation model. Over 93% of the model translations are parseable, suggesting that it learns to generate conforming to a grammar. The model has trouble learning the distribution of rarer syntactic rules, and we pinpoint several constructions that differentiate translations between the references and our model.

   @inproceedings{Wei2018HPSG,
     bibtex_show = {true},
     abbr = {BlackboxNLP},
     paper = {https://www.aclweb.org/anthology/W18-5432.pdf},
     address = {Brussels, Belgium},
     author = {Wei, Johnny and Pham, Khiem and O{'}Connor, Brendan and Dillon, Brian},
     booktitle = {Proceedings of the 2018 {EMNLP} Workshop {B}lackbox{NLP}: Analyzing and Interpreting Neural Networks for {NLP}},
     date-added = {2019-09-05 04:54:02 +0000},
     date-modified = {2019-09-05 04:54:10 +0000},
     doi = {10.18653/v1/W18-5432},
     month = nov,
     pages = {298--305},
     publisher = {Association for Computational Linguistics},
     title = {Evaluating Grammaticality in Seq2seq Models with a Broad Coverage {HPSG} Grammar: A Case Study on Machine Translation},
     url = {https://www.aclweb.org/anthology/W18-5432},
     year = {2018},
     bdsk-url-1 = {https://www.aclweb.org/anthology/W18-5432},
     bdsk-url-2 = {http://dx.doi.org/10.18653/v1/W18-5432}
   }

5. CIKM WS

   Exploring Summary-Expanded Entity Embeddings for Entity Retrieval

   Shahrzad Naseri, John Foley, James Allan, and Brendan O’Connor

   2018

   Paper Bib

   @inproceedings{Naseri2018Entity,
     bibtex_show = {true},
     abbr = {CIKM WS},
     paper = {https://ciir-publications.cs.umass.edu/getpdf.php?id=1362},
     author = {Naseri, Shahrzad and Foley, John and Allan, James and O'Connor, Brendan},
     booktitle = {CEUR Workshop Proceedings (workshop at CIKM)},
     date-added = {2019-09-02 17:47:39 +0000},
     date-modified = {2021-08-11 10:04:56 -0400},
     title = {Exploring Summary-Expanded Entity Embeddings for Entity Retrieval},
     type = {IR},
     year = {2018}
   }

6. COLING

   Authorless Topic Models: Biasing Models Away from Known Structure

   Laure Thompson and David Mimno

   In Proceedings of the 27th International Conference on Computational Linguistics, 2018

   Paper Bib

   @inproceedings{thompson-mimno-2018-authorless,
     abbr = {COLING},
     bibtex_show = {true},
     title = {Authorless Topic Models: Biasing Models Away from Known Structure},
     author = {Thompson, Laure and Mimno, David},
     booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},
     month = aug,
     year = {2018},
     address = {Santa Fe, New Mexico, USA},
     publisher = {Association for Computational Linguistics},
     paper = {https://aclanthology.org/C18-1329},
     pages = {3903--3914}
   }

7. CoNLL

   Embedded-State Latent Conditional Random Fields for Sequence Labeling

   Dung Thai, Sree Harsha Ramesh, Shikhar Murty, Luke Vilnis, and Andrew McCallum

   In Proceedings of the 22nd Conference on Computational Natural Language Learning (CoNLL), 2018

   Paper Bib

   @inproceedings{thai2018embedded,
     title = {Embedded-State Latent Conditional Random Fields for Sequence Labeling},
     abbr = {CoNLL},
     bibtex_show = {true},
     author = {Thai, Dung and Ramesh, Sree Harsha and Murty, Shikhar and Vilnis, Luke and McCallum, Andrew},
     booktitle = {Proceedings of the 22nd Conference on Computational Natural Language Learning (CoNLL)},
     year = {2018},
     paper = {https://arxiv.org/abs/1809.10835}
   }

8. ECIR

   A Neural Passage Model for Ad-hoc Document Retrieval

   Qingyao Ai, Brendan O’Connor, and W. Bruce Croft

   In Advances in Information Retrieval. ECIR 2018 (European Conference on Information Retrieval), 2018

   Bib PDF

   @inproceedings{Ai2018Passage,
     bibtex_show = {true},
     abbr = {ECIR},
     pdf = {https://arxiv.org/pdf/2103.09306.pdf},
     doi = {https://doi.org/10.1007/978-3-319-76941-7_41},
     author = {Ai, Qingyao and O'Connor, Brendan and Croft, W.\ Bruce},
     booktitle = {Advances in Information Retrieval. ECIR 2018 (European Conference on Information Retrieval)},
     date-added = {2019-09-03 01:28:53 +0000},
     date-modified = {2019-09-03 01:29:21 +0000},
     title = {A Neural Passage Model for Ad-hoc Document Retrieval},
     year = {2018}
   }

9. EMNLP

   Revisiting the Importance of Encoding Logic Rules in Sentiment Classification

   Kalpesh Krishna, Preethi Jyothi, and Mohit Iyyer

   In Empirical Methods in Natural Language Processing, 2018

   Paper Bib Code

   @inproceedings{KrishnaRevisit2018,
     abbr = {EMNLP},
     bibtex_show = {true},
     author = {Krishna, Kalpesh and Jyothi, Preethi and Iyyer, Mohit},
     booktitle = {Empirical Methods in Natural Language Processing},
     year = {2018},
     title = {Revisiting the Importance of Encoding Logic Rules in Sentiment Classification},
     paper = {https://arxiv.org/abs/1808.07733},
     code = {https://github.com/martiansideofthemoon/logic-rules-sentiment}
   }

10. EMNLP

    Uncertainty-aware generative models for inferring document class prevalence

    Katherine Keith and Brendan O’Connor

    In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018

    Paper Bib

    Prevalence estimation is the task of inferring the relative frequency of classes of unlabeled examples in a group—for example, the proportion of a document collection with positive sentiment. Previous work has focused on aggregating and adjusting discriminative individual classifiers to obtain prevalence point estimates. But imperfect classifier accuracy ought to be reflected in uncertainty over the predicted prevalence for scientifically valid inference. In this work, we present (1) a generative probabilistic modeling approach to prevalence estimation, and (2) the construction and evaluation of prevalence confidence intervals; in particular, we demonstrate that an off-the-shelf discriminative classifier can be given a generative re-interpretation, by backing out an implicit individual-level likelihood function, which can be used to conduct fast and simple group-level Bayesian inference. Empirically, we demonstrate our approach provides better confidence interval coverage than an alternative, and is dramatically more robust to shifts in the class prior between training and testing.

    @inproceedings{Keith2018DocPropor,
      bibtex_show = {true},
      abbr = {EMNLP},
      paper = {https://www.aclweb.org/anthology/D18-1487.pdf},
      address = {Brussels, Belgium},
      author = {Keith, Katherine and O{'}Connor, Brendan},
      booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
      date-added = {2019-09-03 01:33:58 +0000},
      date-modified = {2019-09-03 01:34:18 +0000},
      doi = {10.18653/v1/D18-1487},
      month = oct,
      pages = {4575--4585},
      publisher = {Association for Computational Linguistics},
      title = {Uncertainty-aware generative models for inferring document class prevalence},
      url = {https://www.aclweb.org/anthology/D18-1487},
      year = {2018},
      bdsk-url-1 = {https://www.aclweb.org/anthology/D18-1487},
      bdsk-url-2 = {http://dx.doi.org/10.18653/v1/D18-1487}
    }

11. EMNLP

    Linguistically-Informed Self-Attention for Semantic Role Labeling

    Emma Strubell, Patrick Verga, Daniel Andor, David Weiss, and Andrew McCallum

    In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP) (Best paper award), 2018

    Paper Bib

    @inproceedings{strubell2018linguistically,
      title = {Linguistically-Informed Self-Attention for Semantic Role Labeling},
      abbr = {EMNLP},
      bibtex_show = {true},
      author = {Strubell, Emma and Verga, Patrick and Andor, Daniel and Weiss, David and McCallum, Andrew},
      booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP) (Best paper award)},
      year = {2018},
      paper = {https://arxiv.org/abs/1804.08199}
    }

12. EMNLP

    Marginal Likelihood Training of BiLSTM-CRF for Biomedical Named Entity Recognition from Disjoint Label Sets

    Nathan Greenberg, Trapit Bansal, Patrick Verga, and Andrew McCallum

    In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP) (Oral), 2018

    Paper Bib

    @inproceedings{greenberg2018marginal,
      title = {Marginal Likelihood Training of BiLSTM-CRF for Biomedical Named Entity Recognition from Disjoint Label Sets},
      abbr = {EMNLP},
      bibtex_show = {true},
      author = {Greenberg, Nathan and Bansal, Trapit and Verga, Patrick and McCallum, Andrew},
      booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP) (Oral)},
      year = {2018},
      paper = {http://aclweb.org/anthology/D18-1306}
    }

13. EMNLP

    QuAC: Question Answering in Context

    Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, and Luke Zettlemoyer

    In Empirical Methods in Natural Language Processing, 2018

    Paper Bib Code

    @inproceedings{ChoiQuAC2018,
      abbr = {EMNLP},
      bibtex_show = {true},
      author = {Choi, Eunsol and He, He and Iyyer, Mohit and Yatskar, Mark and Yih, Wen-tau and Choi, Yejin and Liang, Percy and Zettlemoyer, Luke},
      booktitle = {Empirical Methods in Natural Language Processing},
      year = {2018},
      title = {QuAC: Question Answering in Context},
      paper = {https://arxiv.org/abs/1808.07036},
      code = {http://quac.ai/}
    }

14. EMNLP

    Pathologies of Neural Models Make Interpretation Difficult

    Shi Feng, Eric Wallace, Alvin Grissom II, Mohit Iyyer, Pedro Rodriguez, and Jordan Boyd-Graber

    In Empirical Methods in Natural Language Processing, 2018

    Paper Bib

    @inproceedings{FengRAWR2018,
      abbr = {EMNLP},
      bibtex_show = {true},
      author = {Feng, Shi and Wallace, Eric and II, Alvin Grissom and Iyyer, Mohit and Rodriguez, Pedro and Boyd-Graber, Jordan},
      booktitle = {Empirical Methods in Natural Language Processing},
      year = {2018},
      title = {Pathologies of Neural Models Make Interpretation Difficult},
      paper = {https://arxiv.org/abs/1804.07781}
    }

15. ICLR

    Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning

    Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, and Andrew McCallum

    In International Conference on Learning Representations (ICLR), 2018

    Paper Bib Code

    @inproceedings{das2018go,
      title = {Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning},
      abbr = {ICLR},
      bibtex_show = {true},
      author = {Das, Rajarshi and Dhuliawala, Shehzaad and Zaheer, Manzil and Vilnis, Luke and Durugkar, Ishan and Krishnamurthy, Akshay and Smola, Alex and McCallum, Andrew},
      booktitle = {International Conference on Learning Representations (ICLR)},
      year = {2018},
      paper = {https://arxiv.org/abs/1711.05851},
      code = {https://github.com/shehzaadzd/MINERVA}
    }

16. NAACL

    Adversarial Example Generation with Syntactically Controlled Paraphrase Networks

    Mohit Iyyer, John Wieting, Kevin Gimpel, and Luke Zettlemoyer

    In North American Association for Computational Linguistics, 2018

    Paper Bib Code

    @inproceedings{IyyerSCPN2018,
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Iyyer, Mohit and Wieting, John and Gimpel, Kevin and Zettlemoyer, Luke},
      booktitle = {North American Association for Computational Linguistics},
      year = {2018},
      title = {Adversarial Example Generation with Syntactically Controlled Paraphrase Networks},
      paper = {https://arxiv.org/abs/1804.06059},
      code = {https://github.com/miyyer/scpn}
    }

17. NAACL

    Simultaneously Self-attending to All Mentions for Full-Abstract Biological Relation Extraction

    Patrick Verga, Emma Strubell, and Andrew McCallum

    In Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), 2018

    Paper Bib Code

    @inproceedings{DBLP:conf/naacl/Verga18,
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Verga, Patrick and Strubell, Emma and McCallum, Andrew},
      title = {Simultaneously Self-attending to All Mentions for Full-Abstract Biological Relation Extraction },
      booktitle = {Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL)},
      year = {2018},
      paper = {https://arxiv.org/abs/1802.10569},
      code = {https://github.com/patverga/bran}
    }

18. NAACL

    Training Structured Prediction Energy Networks with Indirect Supervision

    Amirmohammad Rooshenas, Aishwarya Kamath, and Andrew McCallum

    In Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL) (Oral), 2018

    Bib

    @inproceedings{DBLP:conf/naacl/Rooshenas18,
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Rooshenas, Amirmohammad and Kamath, Aishwarya and McCallum, Andrew},
      title = {Training Structured Prediction Energy Networks with Indirect Supervision},
      booktitle = {Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL) (Oral)},
      year = {2018}
    }

19. NAACL

    Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection

    Haw-Shiuan Chang, ZiYun Wang, Luke Vilnis, and Andrew McCallum

    In Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), 2018

    Paper Bib Code Poster

    @inproceedings{chang2017unsupervised,
      title = {Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection},
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Chang, Haw-Shiuan and Wang, ZiYun and Vilnis, Luke and McCallum, Andrew},
      booktitle = {Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL)},
      paper = {http://arxiv.org/abs/1710.00880},
      year = {2018},
      code = {https://github.com/iesl/Distributional-Inclusion-Vector-Embedding},
      poster = {http://docs.wixstatic.com/ugd/e150d8_925731e34b974de881cbe54f66807d36.pdf},
      demo = {https://bl.ocks.org/chsu5358/raw/f08d4755b0f04e113c139a72a977df5c/}
    }

20. NAACL

    Deep contextualized word representations

    Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer

    In North American Association for Computational Linguistics, 2018

    Paper Bib Code

    @inproceedings{PetersELMo2018,
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Peters, Matthew E. and Neumann, Mark and Iyyer, Mohit and Gardner, Matt and Clark, Christopher and Lee, Kenton and Zettlemoyer, Luke},
      booktitle = {North American Association for Computational Linguistics},
      year = {2018},
      title = {Deep contextualized word representations},
      paper = {https://arxiv.org/abs/1802.05365},
      code = {https://github.com/allenai/allennlp/blob/master/tutorials/how_to/elmo.md}
    }

21. NAACL

    Learning to Color from Language

    Varun Manjunatha, Mohit Iyyer, Jordan Boyd-Graber, and Larry Davis

    In North American Association for Computational Linguistics, 2018

    Paper Bib Code

    @inproceedings{Manjunatha2018,
      abbr = {NAACL},
      bibtex_show = {true},
      author = {Manjunatha, Varun and Iyyer, Mohit and Boyd-Graber, Jordan and Davis, Larry},
      booktitle = {North American Association for Computational Linguistics},
      year = {2018},
      title = {Learning to Color from Language},
      paper = {https://arxiv.org/abs/1804.06026},
      code = {https://github.com/superhans/colorfromlanguage}
    }

22. NAACL

    Relational Summarization for Corpus Analysis

    Abram Handler and Brendan O’Connor

    In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 2018

    Paper Bib

    This work introduces a new problem, relational summarization, in which the goal is to generate a natural language summary of the relationship between two lexical items in a corpus, without reference to a knowledge base. Motivated by the needs of novel user interfaces, we define the task and give examples of its application. We also present a new query-focused method for finding natural language sentences which express relationships. Our method allows for summarization of more than two times more query pairs than baseline relation extractors, while returning measurably more readable output. Finally, to help guide future work, we analyze the challenges of relational summarization using both a news and a social media corpus.

    @inproceedings{Handler2018Relational,
      bibtex_show = {true},
      abbr = {NAACL},
      paper = {https://www.aclweb.org/anthology/N18-1159.pdf},
      address = {New Orleans, Louisiana},
      author = {Handler, Abram and O{'}Connor, Brendan},
      booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)},
      date-added = {2019-09-03 01:55:26 +0000},
      date-modified = {2019-09-03 01:55:41 +0000},
      doi = {10.18653/v1/N18-1159},
      month = jun,
      pages = {1760--1769},
      publisher = {Association for Computational Linguistics},
      title = {Relational Summarization for Corpus Analysis},
      url = {https://www.aclweb.org/anthology/N18-1159},
      year = {2018},
      bdsk-url-1 = {https://www.aclweb.org/anthology/N18-1159},
      bdsk-url-2 = {http://dx.doi.org/10.18653/v1/N18-1159}
    }

23. NAACL

    Monte Carlo Syntax Marginals for Exploring and Using Dependency Parses

    Katherine Keith, Su Lin Blodgett, and Brendan O’Connor

    In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 2018

    Paper Bib

    Dependency parsing research, which has made significant gains in recent years, typically focuses on improving the accuracy of single-tree predictions. However, ambiguity is inherent to natural language syntax, and communicating such ambiguity is important for error analysis and better-informed downstream applications. In this work, we propose a transition sampling algorithm to sample from the full joint distribution of parse trees defined by a transition-based parsing model, and demonstrate the use of the samples in probabilistic dependency analysis. First, we define the new task of dependency path prediction, inferring syntactic substructures over part of a sentence, and provide the first analysis of performance on this task. Second, we demonstrate the usefulness of our Monte Carlo syntax marginal method for parser error analysis and calibration. Finally, we use this method to propagate parse uncertainty to two downstream information extraction applications: identifying persons killed by police and semantic role assignment.

    @inproceedings{Keith2018MC,
      bibtex_show = {true},
      abbr = {NAACL},
      paper = {http://www.aclweb.org/anthology/N18-1084.pdf},
      address = {New Orleans, Louisiana},
      author = {Keith, Katherine and Blodgett, Su Lin and O'Connor, Brendan},
      booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)},
      date-added = {2018-07-18 14:28:51 +0000},
      date-modified = {2018-07-18 14:29:08 +0000},
      month = jun,
      pages = {917--928},
      publisher = {Association for Computational Linguistics},
      title = {Monte Carlo Syntax Marginals for Exploring and Using Dependency Parses},
      url = {http://www.aclweb.org/anthology/N18-1084},
      year = {2018},
      bdsk-url-1 = {http://www.aclweb.org/anthology/N18-1084}
    }

24. SCiL

    Preface: SCiL 2018 Editors’ Note

    Gaja Jarosz, Brendan O’Connor, and Joe Pater

    Proceedings of the Society for Computation in Linguistics, 2018

    Paper Bib

    @article{Jarosz2018SCiL,
      bibtex_show = {true},
      abbr = {SCiL},
      paper = {https://doi.org/10.7275/R5GF0RQW},
      author = {Jarosz, Gaja and O'Connor, Brendan and Pater, Joe},
      date-added = {2018-11-14 04:37:47 +0000},
      date-modified = {2021-08-11 10:08:26 -0400},
      journal = {Proceedings of the Society for Computation in Linguistics},
      number = {1},
      title = {Preface: {SCiL} 2018 Editors' Note},
      volume = {1},
      year = {2018}
    }

25. SIGIR

    Exploring Diversification In Non-factoid Question Answering

    Lakshmi Vikraman, W. Bruce Croft, and Brendan O’Connor

    In Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval, 2018

    Paper Bib

    @inproceedings{Vikraman2018QA,
      bibtex_show = {true},
      abbr = {SIGIR},
      paper = {https://dl.acm.org/doi/pdf/10.1145/3234944.3234973},
      author = {Vikraman, Lakshmi and Croft, W. Bruce and O'Connor, Brendan},
      booktitle = {Proceedings of the 2018 {ACM} {SIGIR} International Conference on Theory of Information Retrieval},
      date-added = {2019-09-03 01:28:08 +0000},
      date-modified = {2021-08-11 10:03:39 -0400},
      title = {Exploring Diversification In Non-factoid Question Answering},
      year = {2018}
    }

26. SIGIR

    Understanding the Representational Power of Neural Retrieval Models Using NLP Tasks

    Daniel Cohen, Brendan O’Connor, and W. Bruce Croft

    In Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval, 2018

    Paper Bib

    @inproceedings{Cohen2018Interp,
      bibtex_show = {true},
      abbr = {SIGIR},
      paper = {https://dl.acm.org/doi/pdf/10.1145/3234944.3234959},
      author = {Cohen, Daniel and O'Connor, Brendan and Croft, W. Bruce},
      booktitle = {Proceedings of the 2018 {ACM} {SIGIR} International Conference on Theory of Information Retrieval},
      date-added = {2019-09-03 01:27:09 +0000},
      date-modified = {2019-09-05 06:24:36 +0000},
      title = {Understanding the Representational Power of Neural Retrieval Models Using NLP Tasks},
      year = {2018}
    }

27. TextGraphs

    Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings

    Haw-Shiuan Chang, Amol Agrawal, Ananya Ganesh, Anirudha Desai, Vinayak Mathur, Alfred Hough, and Andrew McCallum

    In TextGraphs-12: the Workshop on Graph-based Methods for Natural Language Processing (NAACL WS), 2018

    Paper Bib Slides

    @inproceedings{conf/TextGraph18/Chang18,
      abbr = {TextGraphs},
      bibtex_show = {true},
      author = {Chang, Haw-Shiuan and Agrawal, Amol and Ganesh, Ananya and Desai, Anirudha and Mathur, Vinayak and Hough, Alfred and McCallum, Andrew},
      title = {Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings},
      booktitle = {TextGraphs-12: the Workshop on Graph-based Methods for Natural Language Processing (NAACL WS)},
      year = {2018},
      slides = {http://docs.wixstatic.com/ugd/e150d8_ae5222766cda446985cce83c1c72bae3.pdf},
      paper = {https://arxiv.org/abs/1804.03257}
    }

2017

1. ACL

   Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks

   Rajarshi Das, Manzil Zaheer, Siva Reddy, and Andrew McCallum

   In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), Vancouver, Canada, July 30 - August 4, Volume 2: Short Papers, 2017

   Paper Bib

   @inproceedings{DBLP:conf/acl/DasZRM17,
     abbr = {ACL},
     bibtex_show = {true},
     author = {Das, Rajarshi and Zaheer, Manzil and Reddy, Siva and McCallum, Andrew},
     bibsource = {dblp computer science bibliography, http://dblp.org},
     biburl = {http://dblp.org/rec/bib/conf/acl/DasZRM17},
     booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics ({ACL}), Vancouver, Canada, July 30 - August 4, Volume 2: Short Papers},
     doi = {10.18653/v1/P17-2057},
     editor = {Barzilay, Regina and Kan, Min{-}Yen},
     paper = {https://doi.org/10.18653/v1/P17-2057},
     pages = {358--365},
     publisher = {Association for Computational Linguistics},
     timestamp = {Fri, 04 Aug 2017 16:38:24 +0200},
     title = {Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks},
     year = {2017}
   }

2. AKBC

   Learning String Alignments for Entity Aliases

   Aaron Traylor, Nicholas Monath, Rajarshi Das, and Andrew McCallum

   In 6th Workshop on Automated Knowledge Base Construction (AKBC) 2017 at NIPS, 2017

   Paper Bib Code

   @inproceedings{conf/nips_ws/TraylorMDM17,
     title = {Learning String Alignments for Entity Aliases},
     abbr = {AKBC},
     bibtex_show = {true},
     author = {Traylor, Aaron and Monath, Nicholas and Das, Rajarshi and McCallum, Andrew},
     year = {2017},
     booktitle = {6th Workshop on Automated Knowledge Base Construction (AKBC) 2017 at NIPS},
     paper = {http://www.akbc.ws/2017/papers/28_paper.pdf},
     code = {https://github.com/iesl/learned-string-alignments}
   }

3. AKBC

   RelNet: End-to-end Modeling of Entities & Relations

   Trapit Bansal, Arvind Neelakantan, and Andrew McCallum

   In 6th Workshop on Automated Knowledge Base Construction (AKBC) 2017 at NIPS, 2017

   Paper Bib

   @inproceedings{DBLP:journals/corr/BansalNM17,
     abbr = {AKBC},
     bibtex_show = {true},
     author = {Bansal, Trapit and Neelakantan, Arvind and McCallum, Andrew},
     booktitle = {6th Workshop on Automated Knowledge Base Construction (AKBC) 2017 at NIPS},
     paper = {http://arxiv.org/abs/1706.07179},
     title = {RelNet: End-to-end Modeling of Entities {\&} Relations},
     year = {2017}
   }

4. AKBC

   Entity-centric Attribute Feedback for Interactive Knowledge Bases

   Ari Kobren, Nicholas Monath, and Andrew McCallum

   In 6th Workshop on Automated Knowledge Base Construction (AKBC) 2017 at NIPS, 2017

   Paper Bib

   @inproceedings{conf/nips_ws/KobrenMM17,
     title = {Entity-centric Attribute Feedback for Interactive Knowledge Bases},
     abbr = {AKBC},
     bibtex_show = {true},
     author = {Kobren, Ari and Monath, Nicholas and McCallum, Andrew},
     year = {2017},
     booktitle = {6th Workshop on Automated Knowledge Base Construction (AKBC) 2017 at NIPS},
     paper = {http://www.akbc.ws/2017/papers/27_paper.pdf}
   }

5. DISCML

   Gradient-based Hierarchical Clustering

   Nicholas Monath, Ari Kobren, Akshay Krishnamurthy, and Andrew McCallum

   In NIPS Workshop on Discrete Structures in Machine Learning (DISCML) (Oral), 2017

   Bib

   @inproceedings{conf/nips_ws/MonathKKM17,
     title = {Gradient-based Hierarchical Clustering},
     abbr = {DISCML},
     bibtex_show = {true},
     author = {Monath, Nicholas and Kobren, Ari and Krishnamurthy, Akshay and McCallum, Andrew},
     year = {2017},
     booktitle = {NIPS Workshop on Discrete Structures in Machine Learning (DISCML) (Oral)}
   }

6. DS+J

   Rookie: summarization and visualization for news archives

   Abram Handler and Brendan O’Connor

   Data Science + Journalism Workshop (DS+J) at KDD, 2017

   Paper Bib

   @article{Handler2016RookieDSJ,
     bibtex_show = {true},
     abbr = {DS+J},
     paper = {https://arxiv.org/pdf/1708.01944.pdf},
     author = {Handler, Abram and O'Connor, Brendan},
     date-added = {2017-06-25 17:34:22 +0000},
     date-modified = {2017-06-25 17:35:14 +0000},
     journal = {Data Science + Journalism Workshop ({DS+J}) at {KDD}},
     title = {Rookie: summarization and visualization for news archives},
     year = {2017}
   }

7. EACL

   Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema

   Patrick Verga, Arvind Neelakantan, and Andrew McCallum

   In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Valencia, Spain, April 3-7, 2017, Volume 1: Long Papers (Oral), 2017

   Paper Bib

   @inproceedings{DBLP:conf/eacl/McCallumNV17,
     abbr = {EACL},
     bibtex_show = {true},
     author = {Verga, Patrick and Neelakantan, Arvind and McCallum, Andrew},
     bibsource = {dblp computer science bibliography, http://dblp.org},
     biburl = {http://dblp.org/rec/bib/conf/eacl/McCallumNV17},
     booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics ({EACL}), Valencia, Spain, April 3-7, 2017, Volume 1: Long Papers (Oral)},
     editor = {Lapata, Mirella and Blunsom, Phil and Koller, Alexander},
     paper = {http://aclanthology.info/papers/E17-1058/generalizing-to-unseen-entities-and-entity-pairs-with-row-less-universal-schema},
     pages = {613--622},
     publisher = {Association for Computational Linguistics},
     timestamp = {Wed, 09 Aug 2017 16:04:18 +0200},
     title = {Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema},
     year = {2017},
     data = {https://people.cs.umass.edu/~pat/data/EACL_rowless_entity_types.tar.gz}
   }

8. EACL

   Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks

   Rajarshi Das, Arvind Neelakantan, David Belanger, and Andrew McCallum

   In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Valencia, Spain, April 3-7, 2017, Volume 1: Long Papers, 2017

   Paper Bib Slides

   @inproceedings{DBLP:conf/eacl/McCallumNDB17,
     abbr = {EACL},
     bibtex_show = {true},
     author = {Das, Rajarshi and Neelakantan, Arvind and Belanger, David and McCallum, Andrew},
     bibsource = {dblp computer science bibliography, http://dblp.org},
     biburl = {http://dblp.org/rec/bib/conf/eacl/McCallumNDB17},
     booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics ({EACL}), Valencia, Spain, April 3-7, 2017, Volume 1: Long Papers},
     editor = {Lapata, Mirella and Blunsom, Phil and Koller, Alexander},
     paper = {http://www.aclweb.org/anthology/E17-1013},
     pages = {132--141},
     publisher = {Association for Computational Linguistics},
     timestamp = {Wed, 09 Aug 2017 16:04:18 +0200},
     slides = {http://rajarshd.github.io/talks/Chains_of_Reasoning.pdf},
     title = {Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks},
     year = {2017}
   }

9. EMNLP

   Fast and Accurate Entity Recognition with Iterated Dilated Convolutions

   Emma Strubell, Patrick Verga, David Belanger, and Andrew McCallum

   In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), Copenhagen, Denmark, September 9-11, 2017, 2017

   Paper Bib Code

   @inproceedings{DBLP:conf/emnlp/StrubellVBM17,
     abbr = {EMNLP},
     bibtex_show = {true},
     author = {Strubell, Emma and Verga, Patrick and Belanger, David and McCallum, Andrew},
     bibsource = {dblp computer science bibliography, http://dblp.org},
     biburl = {http://dblp.org/rec/bib/conf/emnlp/StrubellVBM17},
     booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing ({EMNLP}), Copenhagen, Denmark, September 9-11, 2017},
     editor = {Palmer, Martha and Hwa, Rebecca and Riedel, Sebastian},
     paper = {https://arxiv.org/abs/1702.02098},
     pages = {2660--2670},
     publisher = {Association for Computational Linguistics},
     timestamp = {Fri, 15 Sep 2017 17:29:53 +0200},
     title = {Fast and Accurate Entity Recognition with Iterated Dilated Convolutions},
     year = {2017},
     code = {https://github.com/iesl/dilated-cnn-ner}
   }

10. EMNLP

    Identifying civilians killed by police with distantly supervised entity-event extraction

    Katherine Keith, Abram Handler, Michael Pinkham, Cara Magliozzi, Joshua McDuffie, and Brendan O’Connor

    In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017

    Paper Bib

    We propose a new, socially-impactful task for natural language processing: from a news corpus, extract names of persons who have been killed by police. We present a newly collected police fatality corpus, which we release publicly, and present a model to solve this problem that uses EM-based distant supervision with logistic regression and convolutional neural network classifiers. Our model outperforms two off-the-shelf event extractor systems, and it can suggest candidate victim names in some cases faster than one of the major manually-collected police fatality databases.

    @inproceedings{Keith2017PF,
      bibtex_show = {true},
      abbr = {EMNLP},
      paper = {https://www.aclweb.org/anthology/D17-1163.pdf},
      address = {Copenhagen, Denmark},
      author = {Keith, Katherine and Handler, Abram and Pinkham, Michael and Magliozzi, Cara and McDuffie, Joshua and O{'}Connor, Brendan},
      booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
      date-added = {2019-09-03 01:58:34 +0000},
      date-modified = {2019-09-03 01:58:43 +0000},
      doi = {10.18653/v1/D17-1163},
      month = sep,
      pages = {1547--1557},
      publisher = {Association for Computational Linguistics},
      title = {Identifying civilians killed by police with distantly supervised entity-event extraction},
      url = {https://www.aclweb.org/anthology/D17-1163},
      year = {2017},
      bdsk-url-1 = {https://www.aclweb.org/anthology/D17-1163},
      bdsk-url-2 = {http://dx.doi.org/10.18653/v1/D17-1163}
    }

11. EMNLP

    The strange geometry of skip-gram with negative sampling

    David Mimno and Laure Thompson

    In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017

    Paper Bib

    @inproceedings{mimno-thompson-2017-strange,
      abbr = {EMNLP},
      bibtex_show = {true},
      title = {The strange geometry of skip-gram with negative sampling},
      author = {Mimno, David and Thompson, Laure},
      booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
      month = sep,
      year = {2017},
      address = {Copenhagen, Denmark},
      publisher = {Association for Computational Linguistics},
      paper = {https://aclanthology.org/D17-1308},
      doi = {10.18653/v1/D17-1308},
      pages = {2873--2878}
    }

12. FAT/ML

    Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English

    Su Lin Blodgett and Brendan O’Connor

    arXiv preprint arXiv:1707.00061. Presented at Fairness, Accountability, and Transparency in Machine Learning workshop at KDD, 2017

    Paper Bib

    @article{Blodgett2017Disparity,
      bibtex_show = {true},
      abbr = {FAT/ML},
      paper = {https://arxiv.org/pdf/1707.00061.pdf},
      author = {Blodgett, Su Lin and O'Connor, Brendan},
      date-added = {2017-07-15 14:52:43 +0000},
      date-modified = {2019-06-01 03:58:57 +0000},
      journal = {arXiv preprint arXiv:1707.00061. Presented at Fairness, Accountability, and Transparency in Machine Learning workshop at KDD},
      publisher = {Presented at Fairness, Accountability, and Transparency in Machine Learning workshop at KDD 2017},
      title = {Racial Disparity in Natural Language Processing: A Case Study of Social Media {A}frican-{A}merican {E}nglish},
      year = {2017}
    }

13. ICLR

    Learning a Natural Language Interface with Neural Programmer

    Arvind Neelakantan, Quoc V. Le, Martin Abadi, Andrew McCallum, and Dario Amodei

    In International Conference on Learning Representations (ICLR), 2017

    Paper Bib

    @inproceedings{DBLP:conf/iclr/VilnisM16,
      abbr = {ICLR},
      bibtex_show = {true},
      author = {Neelakantan, Arvind and Le, Quoc V. and Abadi, Martin and McCallum, Andrew and Amodei, Dario},
      title = {Learning a Natural Language Interface with Neural Programmer},
      booktitle = {International Conference on Learning Representations (ICLR)},
      year = {2017},
      paper = {http://arxiv.org/abs/1611.08945}
    }

14. ICML

    End-to-End Learning for Structured Prediction Energy Networks

    David Belanger, Bishan Yang, and Andrew McCallum

    In Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, NSW, Australia, 6-11 August 2017, 2017

    Paper Bib

    @inproceedings{DBLP:conf/icml/BelangerYM17,
      abbr = {ICML},
      bibtex_show = {true},
      author = {Belanger, David and Yang, Bishan and McCallum, Andrew},
      bibsource = {dblp computer science bibliography, http://dblp.org},
      biburl = {http://dblp.org/rec/bib/conf/icml/BelangerYM17},
      booktitle = {Proceedings of the 34th International Conference on Machine Learning ({ICML}), Sydney, NSW, Australia, 6-11 August 2017},
      editor = {Precup, Doina and Teh, Yee Whye},
      paper = {http://proceedings.mlr.press/v70/belanger17a.html},
      pages = {429--439},
      publisher = {PMLR},
      series = {Proceedings of Machine Learning Research},
      timestamp = {Wed, 16 Aug 2017 11:08:55 +0200},
      title = {End-to-End Learning for Structured Prediction Energy Networks},
      volume = {70},
      year = {2017}
    }

15. ICML WS

    Low-Rank Hidden State Embeddings for Viterbi Sequence Labeling

    Dung Thai, Shikhar Murty, Trapit Bansal, Luke Vilnis, David Belanger, and Andrew McCallum

    In International Conference on Machine Learning Workshop on Deep Structured Prediction (ICML WS), 2017

    Paper Bib

    @inproceedings{DBLP:conf/icml_ws/Thai17,
      abbr = {ICML WS},
      bibtex_show = {true},
      author = {Thai, Dung and Murty, Shikhar and Bansal, Trapit and Vilnis, Luke and Belanger, David and McCallum, Andrew},
      title = {Low-Rank Hidden State Embeddings for Viterbi Sequence Labeling},
      booktitle = {International Conference on Machine Learning Workshop on Deep Structured Prediction (ICML WS)},
      year = {2017},
      paper = {http://arxiv.org/abs/1708.00553}
    }

16. ICML WS

    Improved Representation Learning for Predicting Commonsense Ontologies

    Xiang Li, Luke Vilnis, and Andrew McCallum

    In International Conference on Machine Learning Workshop on Deep Structured Prediction (ICML WS), 2017

    Paper Bib

    @inproceedings{DBLP:conf/icml_ws/Li17,
      abbr = {ICML WS},
      bibtex_show = {true},
      author = {Li, Xiang and Vilnis, Luke and McCallum, Andrew},
      title = {Improved Representation Learning for Predicting Commonsense Ontologies},
      booktitle = {International Conference on Machine Learning Workshop on Deep Structured Prediction (ICML WS)},
      year = {2017},
      paper = {http://arxiv.org/abs/1708.00549}
    }

17. NIPS

    Active Bias: Training a More Accurate Neural Network by Emphasizing High Variance Samples

    Haw-Shiuan Chang, Erik G. Learned-Miller, and Andrew McCallum

    In Advances in Neural Information Processing Systems (NIPS), 2017

    Paper Bib Poster

    @inproceedings{DBLP:conf/nips/ChangLM17,
      abbr = {NIPS},
      bibtex_show = {true},
      author = {Chang, Haw{-}Shiuan and Learned{-}Miller, Erik G. and McCallum, Andrew},
      title = {Active Bias: Training a More Accurate Neural Network by Emphasizing
                     High Variance Samples},
      booktitle = {Advances in Neural Information Processing Systems (NIPS)},
      year = {2017},
      poster = {http://people.umass.edu/hawshiuancha/NIPS_poster_active_bias.pdf},
      paper = {http://arxiv.org/abs/1704.07433}
    }

18. NIPS WS

    Automatically Extracting Action Graphs from Materials Science Synthesis Procedures

    Sheshera Mysore, Edward Kim, Emma Strubell, Ao Liu, Haw-Shiuan Chang, Srikrishna Kompella, Kevin Huang, Andrew McCallum, and Elsa Olivetti

    In Workshop on Machine Learning for Molecules and Materials at NIPS, 2017

    Paper Bib

    @inproceedings{mysore2017automatically,
      title = {Automatically Extracting Action Graphs from Materials Science Synthesis Procedures},
      abbr = {NIPS WS},
      bibtex_show = {true},
      author = {Mysore, Sheshera and Kim, Edward and Strubell, Emma and Liu, Ao and Chang, Haw-Shiuan and Kompella, Srikrishna and Huang, Kevin and McCallum, Andrew and Olivetti, Elsa},
      booktitle = {Workshop on Machine Learning for Molecules and Materials at NIPS},
      year = {2017},
      paper = {https://arxiv.org/abs/1711.06872}
    }

19. NLP+CSS

    Proceedings of the Second Workshop on NLP and Computational Social Science

    Dirk Hovy, Svitlana Volkova, David Bamman, David Jurgens, Brendan O’Connor, Oren Tsur, and A. Seza Doğruöz

    2017

    Paper Bib

    @proceedings{Hovy2017NLPCSS,
      bibtex_show = {true},
      abbr = {NLP+CSS},
      paper = {https://www.aclweb.org/anthology/W17-2900},
      address = {Vancouver, Canada},
      author = {Hovy, Dirk and Volkova, Svitlana and Bamman, David and Jurgens, David and O{'}Connor, Brendan and Tsur, Oren and Do{\u{g}}ru{\"o}z, A. Seza},
      date-added = {2019-09-03 01:39:11 +0000},
      date-modified = {2019-09-03 01:39:19 +0000},
      doi = {10.18653/v1/W17-29},
      month = aug,
      publisher = {Association for Computational Linguistics},
      title = {Proceedings of the Second Workshop on {NLP} and Computational Social Science},
      url = {https://www.aclweb.org/anthology/W17-2900},
      year = {2017},
      bdsk-url-1 = {https://www.aclweb.org/anthology/W17-2900},
      bdsk-url-2 = {http://dx.doi.org/10.18653/v1/W17-29}
    }

20. SIGKDD

    A Hierarchical Algorithm for Extreme Clustering

    Ari Kobren, Nicholas Monath, Akshay Krishnamurthy, and Andrew McCallum

    In Proceedings of the 23rd ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), Halifax, NS, Canada, August 13 - 17, 2017 (Oral), 2017

    Paper Bib Code Talk

    @inproceedings{DBLP:conf/kdd/KobrenMKM17,
      abbr = {SIGKDD},
      bibtex_show = {true},
      author = {Kobren, Ari and Monath, Nicholas and Krishnamurthy, Akshay and McCallum, Andrew},
      bibsource = {dblp computer science bibliography, http://dblp.org},
      biburl = {http://dblp.org/rec/bib/conf/kdd/KobrenMKM17},
      booktitle = {Proceedings of the 23rd {ACM} International Conference on Knowledge Discovery and Data Mining ({SIGKDD}), Halifax, NS, Canada, August 13 - 17, 2017 (Oral)},
      doi = {10.1145/3097983.3098079},
      paper = {http://www.kdd.org/kdd2017/papers/view/an-online-hierarchical-algorithm-for-extreme-clustering},
      pages = {255--264},
      publisher = {ACM},
      timestamp = {Tue, 15 Aug 2017 16:10:36 +0200},
      title = {A Hierarchical Algorithm for Extreme Clustering},
      year = {2017},
      code = {https://github.com/iesl/xcluster},
      video = {http://videolectures.net/kdd2017_kobren_extreme_clustering/}
    }

21. SPNLP

    Dependency Parsing with Dilated Iterated Graph CNNs

    Emma Strubell and Andrew McCallum

    In Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing (SPNLP at EMNLP), Copenhagen, Denmark, September 2017, 2017

    Paper Bib

    @inproceedings{DBLP:conf/emnlp/StrubellM17,
      abbr = {SPNLP},
      bibtex_show = {true},
      author = {Strubell, Emma and McCallum, Andrew},
      bibsource = {dblp computer science bibliography, http://dblp.org},
      biburl = {http://dblp.org/rec/bib/conf/emnlp/StrubellM17},
      booktitle = {Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing (SPNLP at EMNLP), Copenhagen, Denmark, September 2017},
      editor = {Chang, Kai{-}Wei and Chang, Ming{-}Wei and Srikumar, Vivek and Rush, Alexander M.},
      paper = {http://aclanthology.info/papers/W17-4301/w17-4301},
      pages = {1--6},
      publisher = {Association for Computational Linguistics},
      timestamp = {Mon, 18 Sep 2017 12:23:03 +0200},
      title = {Dependency Parsing with Dilated Iterated Graph CNNs},
      year = {2017}
    }

22. SemEval

    SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications

    Isabelle Augenstein, Mrinal Das, Sebastian Riedel, Lakshmi Vikraman, and Andrew McCallum

    In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval at ACL), Vancouver, Canada, August 3-4, 2017, 2017

    Paper Bib

    @inproceedings{DBLP:conf/semeval/AugensteinDRVM17,
      abbr = {SemEval},
      bibtex_show = {true},
      author = {Augenstein, Isabelle and Das, Mrinal and Riedel, Sebastian and Vikraman, Lakshmi and McCallum, Andrew},
      bibsource = {dblp computer science bibliography, http://dblp.org},
      biburl = {http://dblp.org/rec/bib/conf/semeval/AugensteinDRVM17},
      booktitle = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval at ACL), Vancouver, Canada, August 3-4, 2017},
      doi = {10.18653/v1/S17-2091},
      editor = {Bethard, Steven and Carpuat, Marine and Apidianaki, Marianna and Mohammad, Saif M. and Cer, Daniel M. and Jurgens, David},
      paper = {http://www.aclweb.org/anthology/S17-2091},
      pages = {546--555},
      publisher = {Association for Computational Linguistics},
      timestamp = {Wed, 16 Aug 2017 01:00:00 +0200},
      title = {SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications},
      year = {2017}
    }

23. WNUT

    A Dataset and Classifier for Recognizing Social Media English

    Su Lin Blodgett, Johnny Wei, and Brendan O’Connor

    In Proceedings of the 3rd Workshop on Noisy User-generated Text, 2017

    Paper Bib

    While language identification works well on standard texts, it performs much worse on social media language, in particular dialectal language—even for English. First, to support work on English language identification, we contribute a new dataset of tweets annotated for English versus non-English, with attention to ambiguity, code-switching, and automatic generation issues. It is randomly sampled from all public messages, avoiding biases towards pre-existing language classifiers. Second, we find that a demographic language model—which identifies messages with language similar to that used by several U.S. ethnic populations on Twitter—can be used to improve English language identification performance when combined with a traditional supervised language identifier. It increases recall with almost no loss of precision, including, surprisingly, for English messages written by non-U.S. authors. Our dataset and identifier ensemble are available online.

    @inproceedings{Blodgett2017LID,
      bibtex_show = {true},
      abbr = {WNUT},
      paper = {https://www.aclweb.org/anthology/W17-4408.pdf},
      address = {Copenhagen, Denmark},
      author = {Blodgett, Su Lin and Wei, Johnny and O{'}Connor, Brendan},
      booktitle = {Proceedings of the 3rd Workshop on Noisy User-generated Text},
      date-added = {2019-09-03 01:56:08 +0000},
      date-modified = {2019-09-03 01:56:15 +0000},
      doi = {10.18653/v1/W17-4408},
      month = sep,
      pages = {56--61},
      publisher = {Association for Computational Linguistics},
      title = {A Dataset and Classifier for Recognizing Social Media {E}nglish},
      url = {https://www.aclweb.org/anthology/W17-4408},
      year = {2017},
      bdsk-url-1 = {https://www.aclweb.org/anthology/W17-4408},
      bdsk-url-2 = {http://dx.doi.org/10.18653/v1/W17-4408}
    }

24. WWW

    Learning to Extract Events from Knowledge Base Revisions

    Alexander Konovalov, Benjamin Strauss, Alan Ritter, and Brendan O’Connor

    In Proceedings of the 26th International Conference on World Wide Web, 2017

    Paper Bib

    @inproceedings{Konovalov2017Events,
      bibtex_show = {true},
      abbr = {WWW},
      paper = {http://brenocon.com/konovalov2017events.pdf},
      author = {Konovalov, Alexander and Strauss, Benjamin and Ritter, Alan and O'Connor, Brendan},
      booktitle = {Proceedings of the 26th International Conference on World Wide Web},
      date-added = {2017-06-25 17:36:01 +0000},
      date-modified = {2017-06-25 17:36:22 +0000},
      organization = {International World Wide Web Conferences Steering Committee},
      pages = {1007--1014},
      title = {Learning to Extract Events from Knowledge Base Revisions},
      year = {2017}
    }

2016

1. AKBC

   Row-less Universal Schema

   Patrick Verga and Andrew McCallum

   In Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016 (Oral), 2016

   Paper Bib

   @inproceedings{DBLP:conf/akbc/VergaM16,
     abbr = {AKBC},
     bibtex_show = {true},
     author = {Verga, Patrick and McCallum, Andrew},
     bibsource = {dblp computer science bibliography, http://dblp.org},
     biburl = {http://dblp.org/rec/bib/conf/akbc/VergaM16},
     booktitle = {Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016 (Oral)},
     editor = {Pujara, Jay and Rockt{\"{a}}schel, Tim and Chen, Danqi and Singh, Sameer},
     paper = {http://aclweb.org/anthology/W/W16/W16-1312.pdf},
     pages = {63--68},
     publisher = {The Association for Computer Linguistics},
     timestamp = {Mon, 19 Sep 2016 17:23:19 +0200},
     title = {Row-less Universal Schema},
     year = {2016}
   }

2. AKBC

   Incorporating Selectional Preferences in Multi-hop Relation Extraction

   Rajarshi Das, Arvind Neelakantan, David Belanger, and Andrew McCallum

   In Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016, 2016

   Paper Bib

   @inproceedings{DBLP:conf/akbc/DasNBM16,
     abbr = {AKBC},
     bibtex_show = {true},
     author = {Das, Rajarshi and Neelakantan, Arvind and Belanger, David and McCallum, Andrew},
     bibsource = {dblp computer science bibliography, http://dblp.org},
     biburl = {http://dblp.org/rec/bib/conf/akbc/DasNBM16},
     booktitle = {Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016},
     editor = {Pujara, Jay and Rockt{\"{a}}schel, Tim and Chen, Danqi and Singh, Sameer},
     paper = {http://aclweb.org/anthology/W/W16/W16-1304.pdf},
     pages = {18--23},
     publisher = {The Association for Computer Linguistics},
     timestamp = {Mon, 19 Sep 2016 17:23:19 +0200},
     title = {Incorporating Selectional Preferences in Multi-hop Relation Extraction},
     year = {2016}
   }

3. AKBC

   Call for Discussion: Building a New Standard Dataset for Relation Extraction Tasks

   Teresa Martin, Fiete Botschen, Ajay Nagesh, and Andrew McCallum

   In Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016, 2016

   Paper Bib

   @inproceedings{DBLP:conf/akbc/MartinBNM16,
     abbr = {AKBC},
     bibtex_show = {true},
     author = {Martin, Teresa and Botschen, Fiete and Nagesh, Ajay and McCallum, Andrew},
     bibsource = {dblp computer science bibliography, http://dblp.org},
     biburl = {http://dblp.org/rec/bib/conf/akbc/MartinBNM16},
     booktitle = {Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016},
     editor = {Pujara, Jay and Rockt{\"{a}}schel, Tim and Chen, Danqi and Singh, Sameer},
     paper = {http://aclweb.org/anthology/W/W16/W16-1317.pdf},
     pages = {92--96},
     publisher = {The Association for Computer Linguistics},
     timestamp = {Mon, 19 Sep 2016 17:23:19 +0200},
     title = {Call for Discussion: Building a New Standard Dataset for Relation Extraction Tasks},
     year = {2016}
   }

4. CIKM

   Improving Entity Ranking for Keyword Queries

   John Foley, Brendan O’Connor, and James Allan

   In Proceedings of CIKM, 2016

   Paper Bib

   @inproceedings{Foley2016Ranking,
     bibtex_show = {true},
     abbr = {CIKM},
     paper = {http://maroo.cs.umass.edu/getpdf.php?id=1223},
     author = {Foley, John and O'Connor, Brendan and Allan, James},
     booktitle = {Proceedings of {CIKM}},
     date-added = {2016-08-29 14:32:10 +0000},
     date-modified = {2016-08-29 21:02:55 +0000},
     title = {Improving Entity Ranking for Keyword Queries},
     year = {2016}
   }

5. EMNLP

   Demographic Dialectal Variation in Social Media: A Case Study of African-American English

   Su Lin Blodgett, Lisa Green, and Brendan O’Connor

   Proceedings of EMNLP, 2016

   Paper Bib

   @article{Blodgett2016AAE,
     bibtex_show = {true},
     abbr = {EMNLP},
     paper = {https://aclanthology.org/D16-1120.pdf},
     author = {Blodgett, Su Lin and Green, Lisa and O'Connor, Brendan},
     date-added = {2016-07-19 02:19:28 +0000},
     date-modified = {2016-07-31 16:48:45 +0000},
     journal = {Proceedings of {EMNLP}},
     title = {Demographic Dialectal Variation in Social Media: A Case Study of {A}frican-{A}merican {E}nglish},
     year = {2016}
   }

6. ICML

   Structured Prediction Energy Networks

   David Belanger and Andrew McCallum

   In Proceedings of the 33rd International Conference on Machine Learning (ICML), New York City, NY, USA, June 19-24, 2016, 2016

   Paper Bib

   @inproceedings{DBLP:conf/icml/BelangerM16,
     abbr = {ICML},
     bibtex_show = {true},
     author = {Belanger, David and McCallum, Andrew},
     bibsource = {dblp computer science bibliography, http://dblp.org},
     biburl = {http://dblp.org/rec/bib/conf/icml/BelangerM16},
     booktitle = {Proceedings of the 33rd International Conference on Machine Learning ({ICML}), New York City, NY, USA, June 19-24, 2016},
     editor = {Balcan, Maria{-}Florina and Weinberger, Kilian Q.},
     paper = {http://jmlr.org/proceedings/papers/v48/belanger16.html},
     pages = {983--992},
     publisher = {JMLR.org},
     series = {{JMLR} Workshop and Conference Proceedings},
     timestamp = {Tue, 12 Jul 2016 21:51:16 +0200},
     title = {Structured Prediction Energy Networks},
     volume = {48},
     year = {2016}
   }

7. NAACL

   Multilingual Relation Extraction using Compositional Universal Schema

   Patrick Verga, David Belanger, Emma Strubell, Benjamin Roth, and Andrew McCallum

   In NAACL HLT 2016, The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT/NAACL), San Diego California, USA, June 12-17, 2016 (Oral), 2016

   Paper Bib Code

   @inproceedings{DBLP:conf/naacl/VergaBSRM16,
     abbr = {NAACL},
     bibtex_show = {true},
     author = {Verga, Patrick and Belanger, David and Strubell, Emma and Roth, Benjamin and McCallum, Andrew},
     bibsource = {dblp computer science bibliography, http://dblp.org},
     biburl = {http://dblp.org/rec/bib/conf/naacl/VergaBSRM16},
     booktitle = {{NAACL} {HLT} 2016, The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT/NAACL), San Diego California, USA, June 12-17, 2016 (Oral)},
     editor = {Knight, Kevin and Nenkova, Ani and Rambow, Owen},
     paper = {http://aclweb.org/anthology/N/N16/N16-1103.pdf},
     pages = {886--896},
     publisher = {The Association for Computational Linguistics},
     timestamp = {Tue, 13 Sep 2016 19:52:39 +0200},
     title = {Multilingual Relation Extraction using Compositional Universal Schema},
     year = {2016},
     code = {https://github.com/patverga/torch-relation-extraction},
     data = {https://people.cs.umass.edu/~pat/data/naacl-data.tar.gz}
   }

8. NLP+CSS

   Proceedings of the First Workshop on NLP and Computational Social Science

   David Bamman, A. Seza Doğruöz, Jacob Eisenstein, Dirk Hovy, David Jurgens, Brendan O’Connor, Alice Oh, Oren Tsur, and Svitlana Volkova

   2016

   Paper Bib

   @proceedings{Hovy2016NLPCSS,
     bibtex_show = {true},
     abbr = {NLP+CSS},
     paper = {https://www.aclweb.org/anthology/W16-5600},
     address = {Austin, Texas},
     author = {Bamman, David and Do{\u{g}}ru{\"o}z, A. Seza and Eisenstein, Jacob and Hovy, Dirk and Jurgens, David and O{'}Connor, Brendan and Oh, Alice and Tsur, Oren and Volkova, Svitlana},
     date-added = {2019-09-03 01:39:27 +0000},
     date-modified = {2019-09-03 01:39:35 +0000},
     doi = {10.18653/v1/W16-56},
     month = nov,
     publisher = {Association for Computational Linguistics},
     title = {Proceedings of the First Workshop on {NLP} and Computational Social Science},
     url = {https://www.aclweb.org/anthology/W16-5600},
     year = {2016},
     bdsk-url-1 = {https://www.aclweb.org/anthology/W16-5600},
     bdsk-url-2 = {http://dx.doi.org/10.18653/v1/W16-56}
   }

9. NLP+CSS

   Bag of what? Simple noun phrase extraction for corpus analysis

   Abram Handler, Matt Denny, Hanna Wallach, and Brendan O’Connor

   In Proceedings of EMNLP: NLP+CSS: Workshop in Natural Language Processing and Computational Social Science, 2016

   Paper Bib

   @inproceedings{Handler2016Phrases,
     bibtex_show = {true},
     abbr = {NLP+CSS},
     paper = {https://aclanthology.org/W16-5615.pdf},
     author = {Handler, Abram and Denny, Matt and Wallach, Hanna and O'Connor, Brendan},
     booktitle = {Proceedings of EMNLP: NLP+CSS: Workshop in Natural Language Processing and Computational Social Science},
     date-added = {2016-09-21 17:42:40 +0000},
     date-modified = {2016-09-21 17:45:11 +0000},
     title = {Bag of what? Simple noun phrase extraction for corpus analysis},
     year = {2016}
   }

10. RecSys

    Ask the GRU: Multi-task Learning for Deep Text Recommendations

    Trapit Bansal, David Belanger, and Andrew McCallum

    In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys), Boston, MA, USA, September 15-19, 2016, 2016

    Paper Bib

    @inproceedings{DBLP:conf/recsys/BansalBM16,
      abbr = {RecSys},
      bibtex_show = {true},
      author = {Bansal, Trapit and Belanger, David and McCallum, Andrew},
      bibsource = {dblp computer science bibliography, http://dblp.org},
      biburl = {http://dblp.org/rec/bib/conf/recsys/BansalBM16},
      booktitle = {Proceedings of the 10th {ACM} Conference on Recommender Systems (RecSys), Boston, MA, USA, September 15-19, 2016},
      doi = {10.1145/2959100.2959180},
      editor = {Sen, Shilad and Geyer, Werner and Freyne, Jill and Castells, Pablo},
      paper = {http://doi.acm.org/10.1145/2959100.2959180},
      pages = {107--114},
      publisher = {ACM},
      timestamp = {Wed, 07 Sep 2016 13:42:11 +0200},
      title = {Ask the {GRU}: Multi-task Learning for Deep Text Recommendations},
      year = {2016}
    }

11. TAC/KBP

    Extracting Multilingual Relations under Limited Resources: TAC 2016 Cold-Start KB construction and Slot-Filling using Compositional Universal Schema

    Haw-Shiuan Chang, Abdurrahman Munir, Ao Liu, Johnny Tian-Zheng Wei, Aaron Traylor, Ajay Nagesh, Nicholas Monath, Patrick Verga, Emma Strubell, and Andrew McCallum

    In Text Analysis Conference, Knowledge Base Population (TAC/KBP), 2016

    Paper Bib

    @inproceedings{DBLP:conf/tac/Chang16,
      abbr = {TAC/KBP},
      bibtex_show = {true},
      author = {Chang, Haw-Shiuan and Munir, Abdurrahman and Liu, Ao and Wei, Johnny Tian-Zheng and Traylor, Aaron and Nagesh, Ajay and Monath, Nicholas and Verga, Patrick and Strubell, Emma and McCallum, Andrew},
      title = {Extracting Multilingual Relations under Limited Resources: TAC 2016 Cold-Start KB construction and Slot-Filling using Compositional Universal Schema},
      booktitle = {Text Analysis Conference, Knowledge Base Population (TAC/KBP)},
      year = {2016},
      paper = {https://pdfs.semanticscholar.org/e53e/b683d8380479a8977d4aef0048e26981cdbe.pdf}
    }

12. WHI

    Visualizing textual models with in-text and word-as-pixel highlighting

    Abram Handler, Su Lin Blodgett, and Brendan O’Connor

    arXiv:1606.06352 at Workshop on Human Interpretability in Machine Learning, 2016

    Paper Bib

    @article{Handler2016Visualizing,
      bibtex_show = {true},
      abbr = {WHI},
      paper = {https://arxiv.org/pdf/1606.06352.pdf},
      author = {Handler, Abram and Blodgett, Su Lin and O'Connor, Brendan},
      date-added = {2019-09-05 04:43:04 +0000},
      date-modified = {2019-09-05 04:43:44 +0000},
      journal = {arXiv:1606.06352 at Workshop on Human Interpretability in Machine Learning},
      title = {Visualizing textual models with in-text and word-as-pixel highlighting},
      year = {2016}
    }