default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDHal Daumé III
Person information
- affiliation: University of Maryland, College Park, MD, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j24]Upol Ehsan
, Q. Vera Liao, Samir Passi, Mark O. Riedl, Hal Daumé III:
Seamful XAI: Operationalizing Seamful Design in Explainable AI. Proc. ACM Hum. Comput. Interact. 8(CSCW1): 1-29 (2024)- [c169]Jay Cunningham, Su Lin Blodgett, Michael Madaio, Hal Daumé III, Christina Harrington, Hanna M. Wallach:
Understanding the Impacts of Language Technologies' Performance Disparities on African American Language Speakers. ACL (Findings) 2024: 12826-12833 - [c168]Guowei Xu, Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu, Jiaxin Yuan, Pu Hua, Shuzhen Li, Yanjie Ze, Hal Daumé III, Furong Huang, Huazhe Xu:
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization. ICLR 2024 - [c167]Ruijie Zheng, Ching-An Cheng, Hal Daumé III, Furong Huang, Andrey Kolobov:
PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control. ICML 2024 - [c166]Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Shuang Ma, Hal Daumé III, Huazhe Xu, John Langford, Praveen Palanisamy, Kalyan Shankar Basu, Furong Huang:
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss. ICML 2024 - [c165]Navita Goyal, Connor Baumler, Tin Nguyen, Hal Daumé III:
The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features. IUI 2024: 155-180 - [c164]Chenglei Si, Navita Goyal, Tongshuang Wu, Chen Zhao, Shi Feng, Hal Daumé III, Jordan L. Boyd-Graber:
Large Language Models Help Humans Verify Truthfulness - Except When They Are Convincingly Wrong. NAACL-HLT 2024: 1459-1474 - [i95]Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Shuang Ma, Hal Daumé III, Huazhe Xu, John Langford, Praveen Palanisamy, Kalyan Shankar Basu, Furong Huang:
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss. CoRR abs/2402.06187 (2024) - [i94]Ruijie Zheng, Ching-An Cheng, Hal Daumé III, Furong Huang, Andrey Kolobov:
PRISE: Learning Temporal Action Abstractions as a Sequence Compression Problem. CoRR abs/2402.10450 (2024) - [i93]Lingjun Zhao, Khanh Nguyen, Hal Daumé III:
Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections. CoRR abs/2402.16973 (2024) - [i92]Charvi Rastogi, Xiangchen Song, Zhijing Jin, Ivan Stelmakh, Hal Daumé III, Kun Zhang, Nihar B. Shah:
A Randomized Controlled Trial on Anonymizing Reviewers to Each Other in Peer Review Discussions. CoRR abs/2403.01015 (2024) - [i91]Huy Nghiem, Hal Daumé III:
HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models. CoRR abs/2403.11456 (2024) - [i90]Huy Nghiem, John Prindle, Jieyu Zhao, Hal Daumé III:
"You Gotta be a Doctor, Lin": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations. CoRR abs/2406.12232 (2024) - 2023
- [c163]Arjun Subramonian, Xingdi Yuan, Hal Daumé III, Su Lin Blodgett:
It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance. ACL (Findings) 2023: 3234-3279 - [c162]Lingjun Zhao, Khanh Nguyen, Hal Daumé III:
Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation Models. ACL (Findings) 2023: 3688-3706 - [c161]Eve Fleisig, Aubrie Amstutz, Chad Atalla, Su Lin Blodgett, Hal Daumé III, Alexandra Olteanu, Emily Sheng, Dan Vann, Hanna M. Wallach:
FairPrism: Evaluating Fairness-Related Harms in Text Generation. ACL (1) 2023: 6231-6251 - [c160]Navita Goyal, Ani Nenkova, Hal Daumé III:
Factual or Contextual? Disentangling Error Types in Entity Description Generation. ACL (1) 2023: 8322-8340 - [c159]Connor Baumler, Anna Sotnikova, Hal Daumé III:
Which Examples Should be Multiply Annotated? Active Learning When Annotators May Disagree. ACL (Findings) 2023: 10352-10371 - [c158]Upol Ehsan, Philipp Wintersberger, Elizabeth Anne Watkins, Carina Manger, Gonzalo A. Ramos, Justin D. Weisz, Hal Daumé III, Andreas Riener, Mark O. Riedl:
Human-Centered Explainable AI (HCXAI): Coming of Age. CHI Extended Abstracts 2023: 353:1-353:7 - [c157]Navita Goyal, Eleftheria Briakou, Amanda Liu, Connor Baumler, Claire Bonial, Jeffrey Micher, Clare R. Voss, Marine Carpuat, Hal Daumé III:
What Else Do I Need to Know? The Effect of Background Information on Users' Reliance on QA Systems. EMNLP 2023: 3313-3330 - [c156]Sandra Sandoval, Jieyu Zhao, Marine Carpuat, Hal Daumé III:
A Rose by Any Other Name would not Smell as Sweet: Social Bias in Names Mistranslation. EMNLP 2023: 3933-3945 - [c155]Lingjun Zhao, Khanh Nguyen, Hal Daumé III:
Hallucination Detection for Grounded Instruction Generation. EMNLP (Findings) 2023: 4044-4053 - [c154]Tin Nguyen, Jiannan Xu, Aayushi Roy, Hal Daumé III, Marine Carpuat:
Towards Conceptualization of "Fair Explanation": Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators. EMNLP 2023: 9696-9717 - [c153]Aashaka Desai, Lauren Berger, Fyodor Minakov, Nessa Milano, Chinmay Singh, Kriston Pumphrey, Richard E. Ladner, Hal Daumé III, Alex X. Lu, Naomi Caselli, Danielle Bragg:
ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition. NeurIPS 2023 - [c152]Ruijie Zheng, Xiyao Wang, Yanchao Sun, Shuang Ma, Jieyu Zhao, Huazhe Xu, Hal Daumé III, Furong Huang:
TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning. NeurIPS 2023 - [i89]Lingjun Zhao, Khanh Nguyen, Hal Daumé III:
A Cognitive Evaluation of Instruction Generation Agents tl;dr They Need Better Theory-of-Mind Capabilities. CoRR abs/2301.05149 (2023) - [i88]Aashaka Desai, Lauren Berger, Fyodor O. Minakov, Vanessa Milan, Chinmay Singh, Kriston Pumphrey, Richard E. Ladner, Hal Daumé III, Alex X. Lu, Naomi Caselli, Danielle Bragg:
ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition. CoRR abs/2304.05934 (2023) - [i87]Arjun Subramonian, Xingdi Yuan, Hal Daumé III, Su Lin Blodgett:
It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance. CoRR abs/2305.09022 (2023) - [i86]Navita Goyal, Eleftheria Briakou, Amanda Liu, Connor Baumler, Claire Bonial, Jeffrey Micher, Clare R. Voss, Marine Carpuat, Hal Daumé III:
What Else Do I Need to Know? The Effect of Background Information on Users' Reliance on AI Systems. CoRR abs/2305.14331 (2023) - [i85]Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan K. Baker, Su Lin Blodgett, Hal Daumé III, Jesse Dodge, Ellie Evans, Sara Hooker, Yacine Jernite, Alexandra Sasha Luccioni, Alberto Lusoli, Margaret Mitchell, Jessica Newman, Marie-Therese Png, Andrew Strait, Apostol Vassilev:
Evaluating the Social Impact of Generative AI Systems in Systems and Society. CoRR abs/2306.05949 (2023) - [i84]Ruijie Zheng, Xiyao Wang, Yanchao Sun, Shuang Ma, Jieyu Zhao, Huazhe Xu, Hal Daumé III, Furong Huang:
TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning. CoRR abs/2306.13229 (2023) - [i83]Navita Goyal, Connor Baumler, Tin Nguyen, Hal Daumé III:
The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features. CoRR abs/2310.08617 (2023) - [i82]Chenglei Si, Navita Goyal, Sherry Tongshuang Wu, Chen Zhao, Shi Feng, Hal Daumé III, Jordan L. Boyd-Graber:
Large Language Models Help Humans Verify Truthfulness - Except When They Are Convincingly Wrong. CoRR abs/2310.12558 (2023) - [i81]Ruijie Zheng, Khanh Nguyen, Hal Daumé III, Furong Huang, Karthik Narasimhan:
Progressively Efficient Learning. CoRR abs/2310.13004 (2023) - [i80]Tin Nguyen, Jiannan Xu, Aayushi Roy, Hal Daumé III, Marine Carpuat:
Towards Conceptualization of "Fair Explanation": Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators. CoRR abs/2310.15055 (2023) - [i79]Lingjun Zhao, Khanh Nguyen, Hal Daumé III:
Hallucination Detection for Grounded Instruction Generation. CoRR abs/2310.15319 (2023) - [i78]Guowei Xu, Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu, Jiaxin Yuan, Pu Hua, Shuzhen Li, Yanjie Ze, Hal Daumé III, Furong Huang, Huazhe Xu:
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization. CoRR abs/2310.19668 (2023) - [i77]Yang Trista Cao, Lovely-Frances Domingo, Sarah Ann Gilbert, Michelle L. Mazurek, Katie Shilton, Hal Daumé III:
Toxicity Detection is NOT all you Need: Measuring the Gaps to Supporting Volunteer Content Moderators. CoRR abs/2311.07879 (2023) - [i76]Yang Trista Cao, Anna Sotnikova, Jieyu Zhao, Linda X. Zou, Rachel Rudinger, Hal Daumé III:
Multilingual large language models leak human stereotypes across language boundaries. CoRR abs/2312.07141 (2023) - 2022
- [j23]Matthew Marge, Carol Y. Espy-Wilson, Nigel G. Ward, Abeer Alwan, Yoav Artzi, Mohit Bansal, Gilmer L. Blankenship, Joyce Chai, Hal Daumé III, Debadeepta Dey, Mary P. Harper, Thomas Howard, Casey Kennington, Ivana Kruijff-Korbayová, Dinesh Manocha, Cynthia Matuszek, Ross Mead, Raymond J. Mooney, Roger K. Moore, Mari Ostendorf, Heather Pon-Barry, Alexander I. Rudnicky, Matthias Scheutz, Robert St. Amant, Tong Sun, Stefanie Tellex, David R. Traum, Zhou Yu:
Spoken language interaction with robots: Recommendations for future research. Comput. Speech Lang. 71: 101255 (2022) - [j22]Dhanya Sridhar, Hal Daumé III, David M. Blei:
Heterogeneous Supervised Topic Models. Trans. Assoc. Comput. Linguistics 10: 732-745 (2022) - [c151]Upol Ehsan, Philipp Wintersberger, Q. Vera Liao, Elizabeth Anne Watkins, Carina Manger, Hal Daumé III, Andreas Riener, Mark O. Riedl:
Human-Centered Explainable AI (HCXAI): Beyond Opening the Black-Box of AI. CHI Extended Abstracts 2022: 109:1-109:7 - [c150]Amr Sharaf, Hal Daumé III, Renkun Ni:
Promoting Fairness in Learned Models by Learning to Active Learn under Parity Constraints. FAccT 2022: 2149-2156 - [c149]Khanh X. Nguyen, Yonatan Bisk, Hal Daumé III:
A Framework for Learning to Request Rich and Contextually Useful Information from Humans. ICML 2022: 16553-16568 - [c148]Yang Trista Cao, Kyle Seelman, Kyungjun Lee, Hal Daumé III:
What's Different between Visual Question Answering for Machine "Understanding" Versus for Accessibility? AACL/IJCNLP (1) 2022: 1025-1034 - [c147]Kaitlyn Zhou, Su Lin Blodgett, Adam Trischler, Hal Daumé III, Kaheer Suleman, Alexandra Olteanu:
Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications. NAACL-HLT 2022: 314-324 - [c146]Yang Trista Cao, Anna Sotnikova, Hal Daumé III, Rachel Rudinger, Linda Zou:
Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models. NAACL-HLT 2022: 1276-1295 - [i75]Kaitlyn Zhou, Su Lin Blodgett, Adam Trischler, Hal Daumé III, Kaheer Suleman, Alexandra Olteanu:
Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications. CoRR abs/2205.06828 (2022) - [i74]Yang Trista Cao, Anna Sotnikova, Hal Daumé III, Rachel Rudinger, Linda Zou:
Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models. CoRR abs/2206.11684 (2022) - [i73]Yang Trista Cao, Kyle Seelman, Kyungjun Lee, Hal Daumé III:
What's Different between Visual Question Answering for Machine "Understanding" Versus for Accessibility? CoRR abs/2210.14966 (2022) - [i72]Upol Ehsan, Q. Vera Liao, Samir Passi, Mark O. Riedl, Hal Daumé III:
Seamful XAI: Operationalizing Seamful Design in Explainable AI. CoRR abs/2211.06753 (2022) - [i71]Charvi Rastogi, Ivan Stelmakh, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, Jennifer Wortman Vaughan, Zhenyu Xue, Hal Daumé III, Emma Pierson, Nihar B. Shah:
How do Authors' Perceptions of their Papers Compare with Co-authors' Perceptions and Peer-review Decisions? CoRR abs/2211.12966 (2022) - 2021
- [j21]Solon Barocas, Asia J. Biega, Margarita Boyarskaya, Kate Crawford, Hal Daumé III, Miroslav Dudík, Benjamin Fish, Mary L. Gray, Brent J. Hecht, Alexandra Olteanu, Forough Poursabzi-Sangdeh, Luke Stark, Jennifer Wortman Vaughan, Hanna M. Wallach, Marion Zepf:
Responsible computing during COVID-19 and beyond. Commun. ACM 64(7): 30-32 (2021) - [j20]Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna M. Wallach, Hal Daumé III, Kate Crawford:
Datasheets for datasets. Commun. ACM 64(12): 86-92 (2021) - [j19]Yang Trista Cao, Hal Daumé III:
Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle. Comput. Linguistics 47(3): 615-661 (2021) - [j18]Ivan Stelmakh, Nihar B. Shah, Aarti Singh, Hal Daumé III:
Prior and Prejudice: The Novice Reviewers' Bias against Resubmissions in Conference Peer Review. Proc. ACM Hum. Comput. Interact. 5(CSCW1): 75:1-75:17 (2021) - [c145]Ivan Stelmakh, Nihar B. Shah, Aarti Singh, Hal Daumé III:
A Novice-Reviewer Experiment to Address Scarcity of Qualified Reviewers in Large Conferences. AAAI 2021: 4785-4793 - [c144]Amr Sharaf, Hal Daumé III:
Meta-Learning Effective Exploration Strategies for Contextual Bandits. AAAI 2021: 9541-9548 - [c143]Anna Sotnikova, Yang Trista Cao, Hal Daumé III, Rachel Rudinger:
Analyzing Stereotypes in Generative Text Inference Tasks. ACL/IJCNLP (Findings) 2021: 4052-4065 - [c142]Chen Zhao, Chenyan Xiong, Jordan L. Boyd-Graber, Hal Daumé III:
Distantly-Supervised Dense Retrieval Enables Open-Domain Question Answering without Evidence Annotation. EMNLP (1) 2021: 9612-9622 - [c141]David Alvarez-Melis, Harmanpreet Kaur, Hal Daumé III, Hanna M. Wallach, Jennifer Wortman Vaughan:
From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidence. HCOMP 2021: 35-47 - [c140]Chen Zhao, Chenyan Xiong, Jordan L. Boyd-Graber, Hal Daumé III:
Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval. NAACL-HLT 2021: 4635-4641 - [i70]Chen Zhao, Chenyan Xiong, Jordan L. Boyd-Graber, Hal Daumé III:
Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval. CoRR abs/2104.05883 (2021) - [i69]David Alvarez-Melis, Harmanpreet Kaur, Hal Daumé III, Hanna M. Wallach, Jennifer Wortman Vaughan:
A Human-Centered Interpretability Framework Based on Weight of Evidence. CoRR abs/2104.13299 (2021) - [i68]Chen Zhao, Chenyan Xiong, Jordan L. Boyd-Graber, Hal Daumé III:
Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation. CoRR abs/2110.04889 (2021) - [i67]Khanh Nguyen, Yonatan Bisk, Hal Daumé III:
Learning When and What to Ask: a Hierarchical Reinforcement Learning Framework. CoRR abs/2110.08258 (2021) - 2020
- [j17]Arti Ramesh, Dan Goldwasser, Bert Huang, Hal Daumé III, Lise Getoor:
Interpretable Engagement Models for MOOCs Using Hinge-Loss Markov Random Fields. IEEE Trans. Learn. Technol. 13(1): 107-122 (2020) - [c139]Kianté Brantley, Hal Daumé III, Amr Sharaf:
Active Imitation Learning with Noisy Guidance. ACL 2020: 2093-2105 - [c138]Yang Trista Cao, Hal Daumé III:
Toward Gender-Inclusive Coreference Resolution. ACL 2020: 4568-4595 - [c137]Su Lin Blodgett, Solon Barocas, Hal Daumé III, Hanna M. Wallach:
Language (Technology) is Power: A Critical Survey of "Bias" in NLP. ACL 2020: 5454-5476 - [c136]Amr Sharaf, Hany Hassan, Hal Daumé III:
Meta-Learning for Few-Shot NMT Adaptation. NGT@ACL 2020: 43-53 - [c135]Tianze Shi, Chen Zhao, Jordan L. Boyd-Graber, Hal Daumé III, Lillian Lee:
On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries. EMNLP (Findings) 2020: 1849-1864 - [c134]Abigail Z. Jacobs, Su Lin Blodgett, Solon Barocas, Hal Daumé III, Hanna M. Wallach:
The meaning and measurement of bias: lessons from natural language processing. FAT* 2020: 706 - [c133]Asia J. Biega, Peter Potash, Hal Daumé III, Fernando Diaz, Michèle Finck:
Operationalizing the Legal Principle of Data Minimization for Personalization. SIGIR 2020: 399-408 - [i66]Amr Sharaf, Hany Hassan, Hal Daumé III:
Meta-Learning for Few-Shot NMT Adaptation. CoRR abs/2004.02745 (2020) - [i65]Shlok Kumar Mishra, Pranav Goel, Abhishek Sharma, Abhyuday Jagannatha, David W. Jacobs, Hal Daumé III:
Towards Automatic Generation of Questions from Long Answers. CoRR abs/2004.05109 (2020) - [i64]Kianté Brantley, Amr Sharaf, Hal Daumé III:
Active Imitation Learning with Noisy Guidance. CoRR abs/2005.12801 (2020) - [i63]Asia J. Biega, Peter Potash, Hal Daumé III, Fernando Diaz, Michèle Finck:
Operationalizing the Legal Principle of Data Minimization for Personalization. CoRR abs/2005.13718 (2020) - [i62]Su Lin Blodgett, Solon Barocas, Hal Daumé III, Hanna M. Wallach:
Language (Technology) is Power: A Critical Survey of "Bias" in NLP. CoRR abs/2005.14050 (2020) - [i61]Khanh Nguyen, Hal Daumé III:
Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithms. CoRR abs/2006.07777 (2020) - [i60]Tianze Shi, Chen Zhao, Jordan L. Boyd-Graber, Hal Daumé III, Lillian Lee:
On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries. CoRR abs/2010.11246 (2020) - [i59]Ivan Stelmakh, Nihar B. Shah, Aarti Singh, Hal Daumé III:
Prior and Prejudice: The Novice Reviewers' Bias against Resubmissions in Conference Peer Review. CoRR abs/2011.14646 (2020) - [i58]Ivan Stelmakh, Nihar B. Shah, Aarti Singh, Hal Daumé III:
A Novice-Reviewer Experiment to Address Scarcity of Qualified Reviewers in Large Conferences. CoRR abs/2011.15050 (2020) - [i57]Ivan Stelmakh, Charvi Rastogi, Nihar B. Shah, Aarti Singh, Hal Daumé III:
A Large Scale Randomized Controlled Trial on Herding in Peer-Review Discussions. CoRR abs/2011.15083 (2020)
2010 – 2019
- 2019
- [j16]Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, Hal Daumé III, John Langford:
Active Learning for Cost-Sensitive Classification. J. Mach. Learn. Res. 20: 65:1-65:50 (2019) - [c132]Yang Trista Cao, Sudha Rao, Hal Daumé III:
Controlling the Specificity of Clarification Question Generation. WNLP@ACL 2019: 53-56 - [c131]Kianté Brantley, Kyunghyun Cho, Hal Daumé III, Sean Welleck:
Non-Monotonic Sequential Text Generation. WNLP@ACL 2019: 57-59 - [c130]Kenneth Holstein, Jennifer Wortman Vaughan, Hal Daumé III, Miroslav Dudík, Hanna M. Wallach:
Improving Fairness in Machine Learning Systems: What Do Industry Practitioners Need? CHI 2019: 600 - [c129]Khanh Nguyen, Hal Daumé III:
Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning. EMNLP/IJCNLP (1) 2019: 684-695 - [c128]Elissa M. Redmiles, Lisa N. Maszkiewicz, Emily Hwang, Dhruv Kuchhal, Everest Liu, Miraida Morales, Denis Peskov, Sudha Rao, Rock Stevens, Kristina Gligoric, Sean Kross, Michelle L. Mazurek, Hal Daumé III:
Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts. EMNLP/IJCNLP (1) 2019: 4830-4841 - [c127]Wen Sun, Alina Beygelzimer, Hal Daumé III, John Langford, Paul Mineiro:
Contextual Memory Trees. ICML 2019: 6026-6035 - [c126]Sean Welleck, Kianté Brantley, Hal Daumé III, Kyunghyun Cho:
Non-Monotonic Sequential Text Generation. ICML 2019: 6716-6726 - [c125]Chicheng Zhang, Alekh Agarwal, Hal Daumé III, John Langford, Sahand Negahban:
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback. ICML 2019: 7335-7344 - [c124]Sudha Rao, Hal Daumé III:
Answer-based Adversarial Training for Generating Clarification Questions. NAACL-HLT (1) 2019: 143-155 - [c123]Sobhan Miryoosefi, Kianté Brantley, Hal Daumé III, Miroslav Dudík, Robert E. Schapire:
Reinforcement Learning with Convex Constraints. NeurIPS 2019: 14070-14079 - [i56]Khanh Nguyen, Hal Daumé III:
Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning. ViGIL@NeurIPS 2019 - [i55]Chicheng Zhang, Alekh Agarwal, Hal Daumé III, John Langford, Sahand N. Negahban:
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback. CoRR abs/1901.00301 (2019) - [i54]Amr Sharaf, Hal Daumé III:
Meta-Learning for Contextual Bandit Exploration. CoRR abs/1901.08159 (2019) - [i53]Sean Welleck, Kianté Brantley, Hal Daumé III, Kyunghyun Cho:
Non-Monotonic Sequential Text Generation. CoRR abs/1902.02192 (2019) - [i52]Sudha Rao, Hal Daumé III:
Answer-based Adversarial Training for Generating Clarification Questions. CoRR abs/1904.02281 (2019) - [i51]Sobhan Miryoosefi, Kianté Brantley, Hal Daumé III, Miroslav Dudík, Robert E. Schapire:
Reinforcement Learning with Convex Constraints. CoRR abs/1906.09323 (2019) - [i50]Khanh Nguyen, Hal Daumé III:
Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning. CoRR abs/1909.01871 (2019) - [i49]Khanh Nguyen, Hal Daumé III:
Global Voices: Crossing Borders in Automatic News Summarization. CoRR abs/1910.00421 (2019) - [i48]David Alvarez-Melis, Hal Daumé III, Jennifer Wortman Vaughan, Hanna M. Wallach:
Weight of Evidence as a Basis for Human-Oriented Explanations. CoRR abs/1910.13503 (2019) - [i47]Yang Trista Cao, Hal Daumé III:
Toward Gender-Inclusive Coreference Resolution. CoRR abs/1910.13913 (2019) - 2018
- [c122]Sudha Rao, Hal Daumé III:
Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information. ACL (1) 2018: 2737-2746 - [c121]Han-Chin Shing, Suraj Nair, Ayah Zirikly, Meir Friedenberg, Hal Daumé III, Philip Resnik:
Expert, Crowdsourced, and Machine Assessment of Suicide Risk via Online Postings. CLPsych@NAACL-HTL 2018: 25-36 - [c120]Chris Kedzie, Kathleen R. McKeown, Hal Daumé III:
Content Selection in Deep Learning Models of Summarization. EMNLP 2018: 1818-1828 - [c119]Hal Daumé III, John Langford, Amr Sharaf:
Residual Loss Prediction: Reinforcement Learning With No Incremental Feedback. ICLR (Poster) 2018 - [c118]Hoang Minh Le, Nan Jiang, Alekh Agarwal, Miroslav Dudík, Yisong Yue, Hal Daumé III:
Hierarchical Imitation and Reinforcement Learning. ICML 2018: 2923-2932 - [c117]Octavian Suciu, Radu Marginean, Yigitcan Kaya, Hal Daumé III, Tudor Dumitras:
When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks. USENIX Security Symposium 2018: 1299-1316 - [i46]Hoang Minh Le, Nan Jiang, Alekh Agarwal, Miroslav Dudík, Yisong Yue, Hal Daumé III:
Hierarchical Imitation and Reinforcement Learning. CoRR abs/1803.00590 (2018) - [i45]