\vspace{.1cm} Students directly advised or co-advised \underline{in underline}. \vspace{.4cm} \headedsection{{\bf \ifumd II.F.2 \fi Preprints / Working Papers}}{}{ \begin{enumerate} \item Pedro Rodriguez, Shi Feng, Mohit Iyyer, He He, and {\bf Jordan Boyd-Graber}. {\bf \href{https://arxiv.org/abs/1904.04792}{Quizbowl: The Case for Incremental Question Answering}}. \emph{ArXiv}, Preprint, 55 pages. \item Benjamin B\"orschinger, {\bf Jordan Boyd-Graber}, Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Michelle Chen Huebscher, Wojciech Gajewski, Yannic Kilcher, Rodrigo Nogueira, and Lierni Sestorain Saralegu. {\bf \href{https://arxiv.org/abs/1911.04156}{Meta Answering for Machine Reading}}. \emph{ArXiv}, Preprint, 10 pages. \end{enumerate} } \headedsection{{\bf 2024}}{}{ \begin{enumerate} \item Srikanth, Neha Pundlik, Rupak Sarkar, Mane, Heran Y., Aparicio, Elizabeth M., Nguyen, Quynh C., Rachel Rudinger, and {\bf Jordan Boyd-Graber}. {\bf Large Language Models Help Humans Verify Truthfulness---Except When They Are Convincingly Wrong}. \emph{North American Association for Computational Linguistics}, 2024. \item Chenglei Si, Navita Goyal, Tongshuang Wu, Chen Zhao, Shi Feng, Hal Daum\'{e} {III}, and Jordan Lee Boyd-Graber. {\bf Large Language Models Help Humans Verify Truthfulness---Except When They Are Convincingly Wrong}. \emph{North American Association for Computational Linguistics}, 2024. \item Quynh C. Nguyen, Elizabeth M. Aparicio, Michelle Jasczynski, Amara Channell Doig, Xiaohe Yue, Heran Mane, Neha Pundlik Srikanth, Francia Ximena Marin Gutierrez, Nataly Delcid, Xin He, and {\bf Jordan Boyd-Graber}. {\bf Randomized Pilot of Rosie, a Health Education Question-and-Answer Chatbot for New Mothers}. \emph{Journal of Medical Internet Research: Journal of Formative Research}, 2024. \item Zongxia Li, Andrew Mao, Daniel Kofi Stephens, Pranav Goel, Emily Walpole, Juan Francisco Fung, Alden Dima, and Jordan Lee Boyd-Graber. {\bf TENOR: Topic Enabled Neural Organization and Recommendation: Evaluating Topic Models in Task Based Settings}. \emph{European Association for Computational Linguistics}, 2024 (21\% Acceptance Rate). \item Ishani Mondal, Shwetha S, Anandhavelu Natarajan, Aparna Garimella, Sambaran Bandyopadhyay, and Jordan Lee Boyd-Graber. {\bf Presentations by the People, for the People: Harnessing LLMs for Generating Persona-Aware Slides from Documents}. \emph{European Association for Computational Linguistics}, 2024 (21\% Acceptance Rate). \end{enumerate} } \headedsection{{\bf 2023}}{}{ \begin{enumerate} \item Mane, Heran Y., Channell Doig, Amara, Marin Gutierrez, Francia Ximena, Jasczynski, Michelle, Yue, Xiaohe, Srikanth, Neha Pundlik, Mane, Sourabh, Sun, Abby, Moats, Rachel Ann, Patel, Pragat, He, Xin, Boyd-Graber, Jordan Lee, Aparicio, Elizabeth M., and Nguyen, Quynh C.. {\bf \href{https://journals.lww.com/jphmp/fulltext/2023/09000/practical_guidance_for_the_development_of_rosie,_a.9.aspx}{Practical Guidance for the Development of Rosie, a Health Education Question-and-Answer Chatbot for New Mothers}}. \emph{Journal of Public Health Management and Practice}, 2023. \item \underline{\href{https://noviscl.github.io/}{Chenglei Si}}, Zhe Gan, Zhengyuan Yang, Shuohang Wang, Jianfeng Wang, {\bf Jordan Boyd-Graber}, and Lijuan Wang. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2023_iclr_reliable.pdf}{Prompting GPT-3 To Be Reliable}}. \emph{International Conference on Learning Representations}, 2023. \item \underline{\href{https://noviscl.github.io/}{Chenglei Si}}, Weijia Shi, Chen Zhao, Luke Zettlemoyer, and Jordan Lee Boyd-Graber. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2023_findings_more.pdf}{Getting \underline{MoRE} out of \underline{M}ixture \underline{o}f Language Model \underline{R}easoning \underline{E}xperts}}. \emph{Findings of Empirical Methods in Natural Language Processing}, 2023 (45\% Acceptance Rate). \item \underline{\href{http://yysung.github.io/}{Yoo Yeon Sung}}, Naeemul Hassan, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2023_emnlp_videoheadline.pdf}{Not all Fake News is Written: A Dataset and Analysis of Misleading Video Headlines}}. \emph{Empirical Methods in Natural Language Processing}, 2023, 9 pages (23\% Acceptance Rate). \item Sander V Schulhoff, Jeremy Pinto, Anaum Khan, Louis-François Bouchard, \underline{\href{https://noviscl.github.io/}{Chenglei Si}}, Jordan Lee Boyd-Graber, Svetlina Anati, Valen Tagliabue, Anson Liu Kost, and Christopher R Carnahan. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2023_emnlp_hackaprompt.pdf}{Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Prompt Hacking Competition}}. \emph{Empirical Methods in Natural Language Processing}, 2023, 9 pages (23\% Acceptance Rate). \item \underline{\href{https://h-j-han.github.io/}{HyoJung Han}}, Marine Carpuat, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2023_emnlp_explicitation.pdf}{Automatic Explicitation to Bridge the Background Knowledge Gap in Translation and its Evaluation with Multilingual QA}}. \emph{Empirical Methods in Natural Language Processing}, 2023, 9 pages (23\% Acceptance Rate). \item Program Chairs' Report on Peer Review at ACL 2023. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2023_acl_peer_review_report.pdf}{Anna Rogers, Marzena Karpinska, Jordan Boyd-Graber, Naoaki Okazaki}}. \emph{Association for Computational Linguistics}, 2023, 33 pages. \end{enumerate} } \headedsection{{\bf 2022}}{}{ \begin{enumerate} \item \underline{\href{https://csel.cs.colorado.edu/~fegu1724/}{Fenfei Guo}}, Chen Zhang, Zhirui Zhang, Qixin He, Kejun Zhang, Jun Xie, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2022_acl_ast.pdf}{Automatic Song Translation for Tonal Languages}}. \emph{Findings of the Association for Computational Linguistics}, 2022, 9 pages (31\% Acceptance Rate). \item \underline{\href{https://noviscl.github.io/}{Chenglei Si}}, Chen Zhao, Sewon Min, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2022_emnlp_calibration.pdf}{Re-Examining Calibration: The Case of Question Answering}}. \emph{Findings of Empirical Methods in Natural Language Processing}, 2022, 9 pages. \item Wanrong He, \underline{Andrew Mao}, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2022_emnlp_cheaters.pdf}{Cheater's Bowl: Human vs. Computer Search Strategies for Open-Domain QA}}. \emph{Findings of Empirical Methods in Natural Language Processing}, 2022, 9 pages. \item Peter Jansen and {\bf Jordan Boyd-Graber}. {\bf \href{https://arxiv.org/abs/2107.08146}{Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language}}. \emph{Figurative Language Workshop 2022 @EMNLP}, 2022. \item \underline{\href{https://h-j-han.github.io/}{HyoJung Han}}, Marine Carpuat, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2022_emnlp_simqa.pdf}{SimQA: Detecting Simultaneous MT Errors through Word-by-Word Question Answering}}. \emph{Empirical Methods in Natural Language Processing}, 2022, 9 pages. \item Shi Feng and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2022_emnlp_augment.pdf}{Learning to Explain Selectively: A Case Study on Question Answering}}. \emph{Empirical Methods in Natural Language Processing}, 2022, 9 pages. \item Yoshinari Fujinuma, {\bf Jordan Boyd-Graber}, and Katharina Kann. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2022_acl_multilingbert.pdf}{How Does Multilingual Pretraining Affect Cross-Lingual Transferability?}}. \emph{Association for Computational Linguistics}, 2022, 9 pages (21\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~myuan/}{Michelle Yuan}}, Patrick Xia, Chandler May, Benjamin Van Durme, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2022_acl_alcoref.pdf}{Adapting Coreference Resolution Models through Active Learning}}. \emph{Association for Computational Linguistics}, 2022, 9 pages (21\% Acceptance Rate). \end{enumerate} } \headedsection{{\bf 2021}}{}{ \begin{enumerate} \item \underline{\href{http://users.umiacs.umd.edu/~chenz/}{Chen Zhao}}, Chenyan Xiong, Hal {Daum\'{e} III}, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2021_naacl_multi_ance.pdf}{Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval}}. \emph{North American Association for Computational Linguistics}, 2021, 6 pages (23\% Acceptance Rate). \item Julian Martin Eisenschlos, Bhuwan Dhingra, Jannis Bulian, Benjamin B\"orschinger, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2021_naacl_fm2.pdf}{Fool Me Twice: Entailment from Wikipedia Gamification}}. \emph{North American Association for Computational Linguistics}, 2021, 10 pages (28\% Acceptance Rate). \item Alexander Hoyle, Pranav Goel, \underline{\href{http://denispeskov.github.io/}{Denis Peskov}}, Andrew Hian-Cheong, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2021_neurips_incoherence.pdf}{Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence}}. \emph{Neural Information Processing Systems}, 2021, 10 pages (26\% Acceptance Rate). \item \underline{\href{http://denispeskov.github.io/}{Denis Peskov}}, Viktor Hangya, {\bf Jordan Boyd-Graber}, and Alexander Fraser. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2021_emnlp_adaptation.pdf}{Adapting Entities across Languages and Cultures}}. \emph{Findings of Empirical Methods in Natural Language Processing}, 2021, 5 pages (37\% Acceptance Rate). \item \underline{\href{https://noviscl.github.io/}{Chenglei Si}}, \underline{\href{http://users.umiacs.umd.edu/~chenz/}{Chen Zhao}}, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2021_emnlp_answer_equiv.pdf}{What's in a Name? Answer Equivalence For Open-Domain Question Answering}}. \emph{Empirical Methods in Natural Language Processing}, 2021, 6 pages (18\% Acceptance Rate). \item Maharshi Gor, Kellie Webster, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2021_emnlp_qa_fairness.pdf}{Toward Deconfounding the Influence of Subject's Demographic Characteristics in Question Answering}}. \emph{Empirical Methods in Natural Language Processing}, 2021, 9 pages (26\% Acceptance Rate). \item \underline{\href{https://www.pedro.ai/}{Pedro Rodriguez}} and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2021_emnlp_paradigms.pdf}{Evaluation Paradigms in Question Answering}}. \emph{Empirical Methods in Natural Language Processing}, 2021, 5 pages (18\% Acceptance Rate). \item \underline{\href{http://users.umiacs.umd.edu/~chenz/}{Chen Zhao}}, Chenyan Xiong, {\bf Jordan Boyd-Graber}, and Hal {Daum\'{e} III}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2021_emnlp_weak_dpr.pdf}{Distantly-Supervised Dense Retrieval Enables Open-Domain Question Answering without Evidence Annotation}}. \emph{Empirical Methods in Natural Language Processing}, 2021, 11 pages (26\% Acceptance Rate). \item \underline{\href{https://www.pedro.ai/}{Pedro Rodriguez}}, Joe Barrow, Alexander Hoyle, John P. Lalor, Robin Jia, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2021_acl_leaderboard.pdf}{Evaluation Examples Are Not Equally Informative: How Should That Change NLP Leaderboards?}}. \emph{Association for Computational Linguistics}, 2021, 9 pages (21\% Acceptance Rate). \end{enumerate} } \headedsection{{\bf 2020}}{}{ \begin{enumerate} \item Francesco Saverio Varini, {\bf Jordan Boyd-Graber}, Massimiliano Ciaramita, and Markus Leippold. {\bf ClimaText: A Dataset for Climate Change Topic Detection}. \emph{NeurIPS Workshop on Tackling Climate Change with Machine Learning}, 2020. \item Diggelmann, Thomas, Boyd-Graber, Jordan, Bulian, Jannis, Ciaramita, Massimiliano, and Leippold, Markus. {\bf \href{https://research.google/pubs/pub50541/}{CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims}}. \emph{NIPS Workshop on Tackling Climate Change with Machine Learning}, 2020. \item \underline{\href{https://csel.cs.colorado.edu/~fegu1724/}{Fenfei Guo}}, {\bf Jordan Boyd-Graber}, Mohit Iyyer, and Leah Findlater. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2020_lrec_sense.pdf}{Which Evaluations Uncover Sense Representations that Actually Make Sense?}}. \emph{Linguistic Resources and Evaluation Conference}, 2020, 10 pages. \item \underline{\href{http://alisonmsmith.github.io/}{Alison Smith}}, Varun Kumar, {\bf Jordan Boyd-Graber}, Kevin Seppi, and Leah Findlater. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2020_iui_control.pdf}{Digging into User Control: Perceptions of Adherence and Instability in Transparent Models}}. \emph{Intelligent User Interfaces}, 2020, 12 pages (23\% Acceptance Rate). \item Tianze Shi, \underline{\href{http://users.umiacs.umd.edu/~chenz/}{Chen Zhao}}, {\bf Jordan Boyd-Graber}, Hal {Daum\'{e} III}, and Lillian Lee. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2020_findings_qalign.pdf}{On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries}}. \emph{Findings of EMNLP}, 2020, 9 pages. \item Wenyan Li, Alvin {Grissom II}, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2020_findings_verbs.pdf}{An Attentive Recurrent Model for Incremental Prediction of Sentence-final Verbs}}. \emph{Findings of EMNLP}, 2020, 9 pages. \item \underline{\href{http://www.cs.umd.edu/~myuan/}{Michelle Yuan}}, \underline{\href{http://users.umiacs.umd.edu/~mozhi/}{Mozhi Zhang}}, Benjamin {Van Durme}, Leah Findlater, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2020_emnlp_clime.pdf}{Interactive Refinement of Cross-Lingual Word Embeddings}}. \emph{Empirical Methods in Natural Language Processing}, 2020, 9 pages (25\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~myuan/}{Michelle Yuan}}, Hsuan-Tien Lin, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2020_emnlp_alps.pdf}{Cold-start Active Learning through Self-Supervised Language Modeling}}. \emph{Empirical Methods in Natural Language Processing}, 2020, 9 pages (25\% Acceptance Rate). \item \underline{\href{http://alisonmsmith.github.io/}{Alison Smith}}, {\bf Jordan Boyd-Graber}, Ron Fan, Melissa Birchfield, Tongshuang Wu, Dan Weld, and Leah Findlater. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2020_chi_explanation.pdf}{No Explainability without Accountability: An Empirical Study of Explanations and Feedback in Interactive ML}}. \emph{Computer-Human Interaction}, 2020 (24\% Acceptance Rate). \item \underline{\href{http://users.umiacs.umd.edu/~mozhi/}{Mozhi Zhang}}, \underline{\href{http://akkikiki.github.io/about/}{Yoshinari Fujinuma}}, and {\bf Jordan Boyd-Graber}. {\bf \href{https://arxiv.org/abs/1812.09617}{Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification}}. \emph{Association for the Advancement of Artificial Intelligence}, 2020, 9 pages (20.6\% Acceptance Rate). \item \underline{\href{http://users.umiacs.umd.edu/~mozhi/}{Mozhi Zhang}}, \underline{\href{http://akkikiki.github.io/about/}{Yoshinari Fujinuma}}, Michael J. Paul, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2020_acl_refine.pdf}{Why Overfitting Isn't Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries}}. \emph{Association for Computational Linguistics}, 2020 (17.6\% Acceptance Rate). \item {\bf Jordan Boyd-Graber} and Benjamin B\"orschinger. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2020_acl_trivia.pdf}{What Question Answering can Learn from Trivia Nerds}}. \emph{Association for Computational Linguistics}, 2020 (25.4\% Acceptance Rate). \item \underline{\href{http://denispeskov.github.io/}{Denis Peskov}}, Benny Cheng, \underline{\href{http://www.cs.umd.edu/~elgohary/}{Ahmed Elgohary Ghoneim}}, Joe Barrow, Cristian Danescu-Niculescu-Mizil, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2020_acl_diplomacy.pdf}{It Takes Two to Lie: One to Lie and One to Listen}}. \emph{Association for Computational Linguistics}, 2020 (25.4\% Acceptance Rate). \item \underline{\href{http://users.umiacs.umd.edu/~chenz/}{Chen Zhao}}, Chenyan Xiong, Xin Qian, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2020_www_delft.pdf}{Complex Factoid Question Answering with a Free-Text Knowledge Graph}}. \emph{ACM International Conference on World Wide Web}, 2020, 11 pages (19.2\% Acceptance Rate). \end{enumerate} } \headedsection{{\bf 2019}}{}{ \begin{enumerate} \item \underline{\href{http://www.ericswallace.com/}{Eric Wallace}}, \underline{\href{https://www.pedro.ai/}{Pedro Rodriguez}}, \underline{\href{http://users.umiacs.umd.edu/~shifeng/}{Shi Feng}}, Ikuya Yamada, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2019_tacl_trick.pdf}{Trick Me If You Can: Human-in-the-loop Generation of Adversarial Question Answering Examples}}. \emph{Transactions of the Association for Computational Linguistics}, 2019, 14 pages. \item Dasha Pruss, \underline{\href{http://akkikiki.github.io/about/}{Yoshinari Fujinuma}}, Ashlynn Daughton, Michael Paul, Brad Arnot, Danielle Szafir, and {\bf Jordan Boyd-Graber}. {\bf \href{https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0216922}{Zika discourse in the Americas: A multilingual topic analysis of {Twitter}}}. \emph{PlosOne}, 2019, 23 pages. \item \underline{\href{http://users.umiacs.umd.edu/~shifeng/}{Shi Feng}} and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2019_iui_augment.pdf}{What AI can do for me: Evaluating Machine Learning Interpretations in Cooperative Play}}. \emph{Intelligent User Interfaces}, 2019 (25\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~elgohary/}{Ahmed Elgohary Ghoneim}}, \underline{\href{http://denispeskov.github.io/}{Denis Peskov}}, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2019_emnlp_sequentialqa.pdf}{Can You Unpack That? Learning to Rewrite Questions-in-Context}}. \emph{Empirical Methods in Natural Language Processing}, 2019, 6 pages. \item \underline{\href{http://www.cs.umd.edu/~wwyang/}{Weiwei Yang}}, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2019_emnlp_mtm.pdf}{A Multilingual Topic Model for Learning Weighted Topic Links Across Incomparable Corpora}}. \emph{Empirical Methods in Natural Language Processing}, 2019, 6 pages. \item \underline{\href{http://denispeskov.github.io/}{Denis Peskov}}, Joe Barrow, \underline{\href{https://www.pedro.ai/}{Pedro Rodriguez}}, Graham Neubig, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2019_interspeech_asr}{Mitigating Noisy Inputs for Question Answering}}. \emph{Conference of the International Speech Communication Association}, 2019, 5 pages. \item Varun Kumar, \underline{\href{http://alisonmsmith.github.io/}{Alison Smith}}, Leah Findlater, Kevin Seppi, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2019_acl_control.pdf}{Why Didn't You Listen to Me? Comparing User Control of Human-in-the-Loop Topic Models}}. \emph{Association for Computational Linguistics}, 2019, 6 pages (18\% Acceptance Rate). \item \underline{\href{http://www.ericswallace.com/}{Eric Wallace}}, \underline{\href{http://users.umiacs.umd.edu/~shifeng/}{Shi Feng}}, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2019_acl_flipside.pdf}{Misleading Failures of Partial-input Baselines}}. \emph{Association for Computational Linguistics}, 2019, 6 pages (18\% Acceptance Rate). \item Jeffrey Lund, Piper Armstrong, Wilson Fearn, Stephen Cowley, Courtni Byun, {\bf Jordan Boyd-Graber}, and Kevin Seppi. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2019_acl_local.pdf}{Automatic and Human Evaluation of Local Topic Quality}}. \emph{Association for Computational Linguistics}, 2019, 10 pages (26\% Acceptance Rate). \item \underline{\href{http://users.umiacs.umd.edu/~mozhi/}{Mozhi Zhang}}, Keyulu Xu, Ken-ichi Kawarabayashi, Stefanie Jegelka, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2019_acl_clwe.pdf}{Are Girls Neko or Sh{\=o}jo? {C}ross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization}}. \emph{Association for Computational Linguistics}, 2019 (18.3\% Acceptance Rate). \item \underline{\href{http://akkikiki.github.io/about/}{Yoshinari Fujinuma}}, Michael Paul, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2019_acl_modularity.pdf}{A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings Based on Graph Modularity}}. \emph{Association for Computational Linguistics}, 2019, 10 pages (26\% Acceptance Rate). \end{enumerate} } \headedsection{{\bf 2018}}{}{ \begin{enumerate} \item {\bf Jordan Boyd-Graber}, \underline{\href{http://users.umiacs.umd.edu/~shifeng/}{Shi Feng}}, and \underline{\href{https://www.pedro.ai/}{Pedro Rodriguez}}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2018_nips_qbcomp.pdf}{Human-Computer Question Answering: The Case for Quizbowl}}. \emph{The NIPS '17 Competition: Building Intelligent Systems}, 2018, 10 pages. \item Aaron Gerow, Yuening Hu, {\bf Jordan Boyd-Graber}, David M. Blei, and James A. Evans. {\bf Measuring Discursive Influence Across Scholarship}. \emph{Proceedings of the National Academies of Science}, 2018. \item Shudong Hao, Michael J. Paul, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2018_naacl_mltm_eval.pdf}{Lessons from the Bible on Modern Topics: Multilingual Topic Model Evaluation on Low-Resource Languages}}. \emph{North American Association for Computational Linguistics}, 2018, 9 pages (35\% Acceptance Rate). \item Mohit Iyyer, Varun Manjunatha, {\bf Jordan Boyd-Graber}, and Larry Davis. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2018_naacl_colorization.pdf}{Learning to Color from Language}}. \emph{North American Association for Computational Linguistics}, 2018, 6 pages (29\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~myuan/}{Michelle Yuan}}, Benjamin {Van Durme}, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2018_neurips_mtanchor.pdf}{Multilingual Anchoring: Interactive Topic Modeling and Alignment Across Languages}}. \emph{Neural Information Processing Systems}, 2018, 10 pages (21\% Acceptance Rate). \item Paul Felt, Eric Ringger, Kevin Seppi, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2018_coling_measurements.pdf}{Learning from Measurements in Crowdsourcing Models: Inferring Ground Truth from Diverse Annotation Types}}. \emph{International Conference on Computational Linguistics}, 2018, 10 pages (37\% Acceptance Rate). \item \underline{\href{http://alisonmsmith.github.io/}{Alison Smith}}, Varun Kumar, {\bf Jordan Boyd-Graber}, Kevin Seppi, and Leah Findlater. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2018_iui_itm.pdf}{User-Centered Design and Evaluation of a Human-in-the-Loop Topic Modeling System}}. \emph{Intelligent User Interfaces}, 2018, 12 pages (23\% Acceptance Rate). \item \underline{\href{http://users.umiacs.umd.edu/~shifeng/}{Shi Feng}}, \underline{\href{http://www.ericswallace.com/}{Eric Wallace}}, Alvin Grissom II, \underline{\href{https://www.pedro.ai/}{Pedro Rodriguez}}, Mohit Iyyer, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2018_emnlp_rs.pdf}{Pathologies of Neural Models Make Interpretation Difficult}}. \emph{Empirical Methods in Natural Language Processing}, 2018, 9 pages (26\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~elgohary/}{Ahmed Elgohary Ghoneim}}, \underline{\href{http://users.umiacs.umd.edu/~chenz/}{Chen Zhao}}, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2018_emnlp_linked.pdf}{Dataset and Baselines for Sequential Open-Domain Question Answering}}. \emph{Empirical Methods in Natural Language Processing}, 2018, 6 pages (23\% Acceptance Rate). \item \underline{\href{http://users.umiacs.umd.edu/~shifeng/}{Shi Feng}}, \underline{\href{http://www.ericswallace.com/}{Eric Wallace}}, and {\bf Jordan Boyd-Graber}. {\bf \href{http://aclweb.org/anthology/W18-5416}{Interpreting Neural Networks with Nearest Neighbors}}. \emph{EMNLP Workshop on BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP}, 2018, 7 pages. \item Craig Stewart, Nikolai Vogler, Junjie Hu, {\bf Jordan Boyd-Graber}, and Graham Neubig. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2018_acl_interpeval.pdf}{Automatic Estimation of Simultaneous Interpreter Performance}}. \emph{Association for Computational Linguistics}, 2018, 5 pages (24\% Acceptance Rate). \item \underline{\href{http://users.umiacs.umd.edu/~mozhi/}{Mozhi Zhang}}, \underline{\href{http://akkikiki.github.io/about/}{Yoshinari Fujinuma}}, and {\bf Jordan Boyd-Graber}. {\bf Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification}. \emph{ACL Workshop on Deep Learning Approaches for Low-Resource Natural Language Processing}, 2018, 6 pages. \item \underline{\href{http://www.ericswallace.com/}{Eric Wallace}} and {\bf Jordan Boyd-Graber}. {\bf \href{http://aclweb.org/anthology/P18-3018}{Trick Me If You Can: Adversarial Writing of Trivia Challenge Questions}}. \emph{ACL Student Research Workshop}, 2018, 6 pages. \end{enumerate} } \headedsection{{\bf 2017}}{}{ \begin{enumerate} \item \underline{\href{http://alisonmsmith.github.io/}{Alison Smith}}, Tak Yeon Lee, \underline{\href{https://www.microsoft.com/en-us/research/people/fopoursa/}{Forough Poursabzi-Sangdeh}}, {\bf Jordan Boyd-Graber}, Kevin Seppi, Niklas Elmqvist, and Leah Findlater. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2017_tacl_eval_tm_viz.pdf}{Evaluating Visual Representations for Topic Understanding and Their Effects on Manually Generated Labels}}. \emph{Transactions of the Association for Computational Linguistics}, 2017, 15 pages. \item {\bf Jordan Boyd-Graber}. {\bf Humans and Computers Working Together to Measure Machine Learning Interpretability}. \emph{The Bridge}, 2017, 5 pages. \item Tak Yeon Lee, \underline{\href{http://alisonmsmith.github.io/}{Alison Smith}}, Kevin Seppi, Niklas Elmqvist, {\bf Jordan Boyd-Graber}, and Leah Findlater. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2017_ijhcs_human_touch.pdf}{The Human Touch: How Non-expert Users Perceive, Interpret, and Fix Topic Models}}. \emph{International Journal of Human-Computer Studies}, 2017, 27 pages. \item You Lu, Jeff Lund, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2017_emnlp_adagrad_olda.pdf}{Why ADAGRAD Fails for Online Topic Modeling}}. \emph{Empirical Methods in Natural Language Processing}, 2017, 6 pages (18\% Acceptance Rate). \item Khanh Nguyen, {\bf Jordan Boyd-Graber}, and Hal {Daum\'{e} III}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2017_emnlp_bandit_mt.pdf}{Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback}}. \emph{Empirical Methods in Natural Language Processing}, 2017, 11 pages (26\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~wwyang/}{Weiwei Yang}}, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2017_emnlp_tree_prior.pdf}{Adapting Topic Models using Lexical Associations with Tree Priors}}. \emph{Empirical Methods in Natural Language Processing}, 2017, 6 pages (18\% Acceptance Rate). \item \underline{\href{https://people.cs.umass.edu/~miyyer/}{Mohit Iyyer}}, Varun Manjunatha, Anupam Guha, Yogarshi Vyas, {\bf Jordan Boyd-Graber}, Hal {Daum\'{e} III}, and Larry Davis. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2017_cvpr_comics.pdf}{The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives}}. \emph{Computer Vision and Pattern Recognition}, 2017, 10 pages (30\% Acceptance Rate). \item \underline{\href{http://alisonmsmith.github.io/}{Alison Smith}}, Varun Kumar, {\bf Jordan Boyd-Graber}, Kevin Seppi, and Leah Findlater. {\bf \href{http://visualization.ischool.uw.edu/hci_uncertainty/papers/Paper11.pdf}{Accounting for Input Uncertainty in Human-in-the-Loop Systems}}. \emph{CHI 2017 Designing for Uncertainty Workshop}, 2017. \item Jeff Lund, Connor Cook, Kevin Seppi, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2017_acl_multiword_anchors.pdf}{Tandem Anchoring: A Multiword Anchor Approach for Interactive Topic Modeling}}. \emph{Association for Computational Linguistics}, 2017, 10 pages (22\% Acceptance Rate). \item {\bf Jordan Boyd-Graber}, Yuening Hu, and David Mimno. {\bf \href{http://www.nowpublishers.com/article/Details/INR-030}{Applications of Topic Models}}. 2017, 153 pages. \end{enumerate} } \headedsection{{\bf 2016}}{}{ \begin{enumerate} \item Daniel Peterson, {\bf Jordan Boyd-Graber}, Martha Palmer, and Daisuke Kawahara. {\bf \href{https://aclanthology.org/S16-2012/}{Leveraging {V}erb{N}et to build Corpus-Specific Verb Clusters}}. \emph{Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics}, 2016, 5 pages. \item \underline{\href{https://hhexiy.github.io/}{He He}}, {\bf Jordan Boyd-Graber}, and Hal {Daum\'{e} III}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2016_naacl_interpretese.pdf}{Interpretese vs. Translationese: The Uniqueness of Human Strategies in Simultaneous Interpretation}}. \emph{North American Association for Computational Linguistics}, 2016, 6 pages (29\% Acceptance Rate). \item \underline{\href{https://people.cs.umass.edu/~miyyer/}{Mohit Iyyer}}, Anupam Guha, Snigdha Chaturvedi, {\bf Jordan Boyd-Graber}, and Hal {Daum\'{e} III}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2016_naacl_relationships.pdf}{Feuding Families and Former Friends: Unsupervised Learning for Dynamic Fictional Relationships}}. \emph{North American Association for Computational Linguistics}, 2016, 11 pages (24\% Acceptance Rate). \item Md Arafat Sultan, {\bf Jordan Boyd-Graber}, and Tamara Sumner. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2016_naacl_sts.pdf}{Bayesian Supervised Domain Adaptation for Short Text Similarity}}. \emph{North American Association for Computational Linguistics}, 2016, 11 pages (24\% Acceptance Rate). \item Anupam Guha, \underline{\href{https://people.cs.umass.edu/~miyyer/}{Mohit Iyyer}}, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2016_naacl_paintings.pdf}{A Distorted Skull Lies in the Bottom Center: Identifying Paintings from Text Descriptions}}. \emph{NAACL Human-Computer Question Answering Workshop}, 2016. \item \underline{\href{http://www.cs.umd.edu/~wwyang/}{Weiwei Yang}}, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf Birds of a Feather in the Same Nest: A Discriminative Topic Model using Block-based Priors}. \emph{Mid-Atlantic Student Colloquium on Speech, Language, and Learning}, 2016. \item \underline{\href{https://hhexiy.github.io/}{He He}}, {\bf Jordan Boyd-Graber}, Kevin Kwok, and Hal {Daum\'{e} III}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2016_icml_opponent.pdf}{Opponent Modeling in Deep Reinforcement Learning}}. \emph{International Conference on Machine Learning}, 2016, 10 pages (24\% Acceptance Rate). \item \underline{\href{https://www.ursinus.edu/live/profiles/3125-alvin-grissom-ii}{Alvin Grissom II}}, Naho Orita, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2016_conll_verbpred.pdf}{Incremental Prediction of Sentence-final Verbs}}. \emph{Conference on Computational Natural Language Learning}, 2016, 10 pages (20\% Acceptance Rate). \item \underline{\href{http://alisonmsmith.github.io/}{Alison Smith}}, Tak Yeon Lee, \underline{\href{https://www.microsoft.com/en-us/research/people/fopoursa/}{Forough Poursabzi-Sangdeh}}, {\bf Jordan Boyd-Graber}, Kevin Seppi, Niklas Elmqvist, and Leah Findlater. {\bf Human-Centered and Interactive: Expanding the Impact of Topic Models}. \emph{CHI Human Centred Machine Learning Workshop}, 2016. \item Evgeny Klochikhin and {\bf Jordan Boyd-Graber}. {\bf Text Analysis}. \emph{Big Data and Social Science Research: Theory and Practical Approaches}, 2016, 27 pages. \item Hadi Amiri, Philip Resnik, {\bf Jordan Boyd-Graber}, and Hal {Daum\'{e} III}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2016_acl_context_ae.pdf}{Learning Text Pair Similarity with Context-sensitive Autoencoders}}. \emph{Association for Computational Linguistics}, 2016 (28\% Acceptance Rate). \item \underline{\href{https://www.microsoft.com/en-us/research/people/fopoursa/}{Forough Poursabzi-Sangdeh}}, {\bf Jordan Boyd-Graber}, Leah Findlater, and Kevin Seppi. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2016_acl_doclabel.pdf}{ALTO: Active Learning with Topic Overviews for Speeding Label Induction and Document Labeling}}. \emph{Association for Computational Linguistics}, 2016 (28\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~wwyang/}{Weiwei Yang}}, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2016_acl_docblock.pdf}{A Discriminative Topic Model using Document Network Structure}}. \emph{Association for Computational Linguistics}, 2016, 10 pages (28\% Acceptance Rate). \end{enumerate} } \headedsection{{\bf 2015}}{}{ \begin{enumerate} \item Anupam Guha, \underline{\href{https://people.cs.umass.edu/~miyyer/}{Mohit Iyyer}}, Danny Bouman, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2015_naacl_qb_coref.pdf}{Removing the Training Wheels: A Coreference Dataset that Entertains Humans and Challenges Computers}}. \emph{North American Association for Computational Linguistics}, 2015, 11 pages (26\% Acceptance Rate). \item \underline{\href{http://www.umiacs.umd.edu/~daithang/}{Thang Nguyen}}, {\bf Jordan Boyd-Graber}, Jeff Lund, Kevin Seppi, and Eric Ringger. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2015_naacl_supervised_anchor.pdf}{Is your anchor going up or down? {F}ast and accurate supervised topic models}}. \emph{North American Association for Computational Linguistics}, 2015, 10 pages (26\% Acceptance Rate). \item {\bf Jordan Boyd-Graber}, \underline{\href{https://people.cs.umass.edu/~miyyer/}{Mohit Iyyer}}, \underline{\href{https://hhexiy.github.io/}{He He}}, and Hal {Daum\'{e} III}. {\bf Interactive Incremental Question Answering}. \emph{Neural Information Processing Systems}, 2015. \item Philip Resnik, William Armstrong, Leonardo Claudino, \underline{\href{http://www.umiacs.umd.edu/~daithang/}{Thang Nguyen}}, \underline{\href{http://www.cs.umd.edu/~vietan/index.htm}{Viet-An Nguyen}}, and {\bf Jordan Boyd-Graber}. {\bf Beyond {LDA}: Exploring Supervised Topic Modeling for Depression-Related Language in Twitter}. \emph{NAACL Workshop on Cognitive Modeling and Computational Linguistics}, 2015. \item \underline{\href{https://www.microsoft.com/en-us/research/people/fopoursa/}{Forough Poursabzi-Sangdeh}} and {\bf Jordan Boyd-Graber}. {\bf Speeding Document Annotation with Topic Models}. \emph{NAACL Student Research Workshop}, 2015. \item Stephen H. Bach, Bert Huang, {\bf Jordan Boyd-Graber}, and Lise Getoor. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2015_icml_paired_dual.pdf}{Paired-Dual Learning for Fast Training of Latent Variable Hinge-Loss MRFs}}. \emph{International Conference on Machine Learning}, 2015, 10 pages (20\% Acceptance Rate). \item \underline{\href{https://hhexiy.github.io/}{He He}}, \underline{\href{https://www.ursinus.edu/live/profiles/3125-alvin-grissom-ii}{Alvin Grissom II}}, {\bf Jordan Boyd-Graber}, and Hal {Daum\'{e} III}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2015_emnlp_rewrite.pdf}{Syntax-based Rewriting for Simultaneous Machine Translation}}. \emph{Empirical Methods in Natural Language Processing}, 2015 (24\% Acceptance Rate). \item Yi Yang, Doug Downey, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2015_emnlp_fast_priors.pdf}{Efficient Methods for Incorporating Knowledge into Topic Models}}. \emph{Empirical Methods in Natural Language Processing}, 2015, 9 pages (24\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~wwyang/}{Weiwei Yang}}, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2015_emnlp_hinge_link.pdf}{Birds of a Feather Linked Together: A Discriminative Topic Model using Link-based Priors}}. \emph{Empirical Methods in Natural Language Processing}, 2015, 5 pages (28\% Acceptance Rate). \item Paul Felt, Eric Ringger, {\bf Jordan Boyd-Graber}, and Kevin Seppi. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2015_conll_cslda.pdf}{Making the Most of Crowdsourced Document Annotations: Confused Supervised {LDA}}}. \emph{Conference on Computational Natural Language Learning}, 2015, 10 pages (30\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~vietan/index.htm}{Viet-An Nguyen}}, {\bf Jordan Boyd-Graber}, Philip Resnik, and Kristina Miler. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2015_acl_teaparty.pdf}{Tea Party in the House: A Hierarchical Ideal Point Topic Model and Its Application to Republican Legislators in the 112th Congress}}. \emph{Association for Computational Linguistics}, 2015, 11 pages (25\% Acceptance Rate). \item Vlad Niculae, Srijan Kumar, {\bf Jordan Boyd-Graber}, and Cristian Danescu-Niculescu-Mizil. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2015_acl_diplomacy.pdf}{Linguistic Harbingers of Betrayal: A Case Study on an Online Strategy Game}}. \emph{Association for Computational Linguistics}, 2015, 10 pages (25\% Acceptance Rate). \item \underline{\href{https://people.cs.umass.edu/~miyyer/}{Mohit Iyyer}}, Varun Manjunatha, {\bf Jordan Boyd-Graber}, and Hal {Daum\'{e} III}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2015_acl_dan.pdf}{Deep Unordered Composition Rivals Syntactic Methods for Text Classification}}. \emph{Association for Computational Linguistics}, 2015, 11 pages (25\% Acceptance Rate). \end{enumerate} } \headedsection{{\bf 2014}}{}{ \begin{enumerate} \item \underline{\href{https://kzhai.github.io/}{Ke Zhai}}, {\bf Jordan Boyd-Graber}, and Shay B. Cohen. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_tacl_ag_vb_online.pdf}{Online Adaptor Grammars with Hybrid Inference}}. \emph{Transactions of the Association for Computational Linguistics}, 2014, 12 pages. \item \underline{Kimberly Glasgow}, Clay Fink, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_icwsm_grief.pdf}{Our grief is unspeakable: Measuring the community impact of a tragedy}}. \emph{The International AAAI Conference on Weblogs and Social Media}, 2014, 9 pages (20\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~vietan/index.htm}{Viet-An Nguyen}}, {\bf Jordan Boyd-Graber}, Philip Resnik, and Jonathan Chang. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_nips_l2h.pdf}{Learning a Concept Hierarchy from Multi-labeled Documents}}. \emph{Neural Information Processing Systems}, 2014, 9 pages (25\% Acceptance Rate). \item \underline{\href{https://people.cs.umass.edu/~miyyer/}{Mohit Iyyer}}, {\bf Jordan Boyd-Graber}, and Hal {Daum\'{e} III}. {\bf Generating Sentences from Semantic Vector Space Representations}. \emph{NIPS Workshop on Learning Semantics}, 2014. \item Jason Chuang, John D. Wilkerson, Rebecca Weiss, Dustin Tingley, Brandon M. Stewart, Margaret E. Roberts, \underline{\href{https://www.microsoft.com/en-us/research/people/fopoursa/}{Forough Poursabzi-Sangdeh}}, Justin Grimmer, Leah Findlater, {\bf Jordan Boyd-Graber}, and Jeffrey Heer. {\bf Computer-Assisted Content Analysis: Topic Models for Exploring Multiple Subjective Interpretations}. \emph{NIPS Workshop on Human-Propelled Machine Learning}, 2014. \item \underline{\href{https://kzhai.github.io/}{Ke Zhai}}, {\bf Jordan Boyd-Graber}, and Shay B. Cohen. {\bf Hybrid Online Inference with Adaptor Grammars}. \emph{NIPS Workshop on Advances in Variational Inference}, 2014. \item \underline{\href{http://www.cs.umd.edu/~vietan/index.htm}{Viet-An Nguyen}}, {\bf Jordan Boyd-Graber}, Philip Resnik, Deborah Cai, Jennifer Midberry, and Yuanxin Wang. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_mlj_influencer.pdf}{Modeling Topic Control to Detect Influence in Conversations using Nonparametric Topic Models}}. \emph{Machine Learning}, 2014, 48 pages. \item \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}}, {\bf Jordan Boyd-Graber}, Brianna Satinoff, and \underline{\href{http://alisonmsmith.github.io/}{Alison Smith}}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_mlj_itm.pdf}{Interactive Topic Modeling}}. \emph{Machine Learning}, 2014, 56 pages. \item {\bf Jordan Boyd-Graber}, David Mimno, and David Newman. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_book_chapter_care_and_feeding.pdf}{Care and Feeding of Topic Models: Problems, Diagnostics, and Improvements}}. \emph{Handbook of Mixed Membership Models and Their Applications}, 2014, 39 pages. \item \underline{\href{http://www.cs.umd.edu/~vietan/index.htm}{Viet-An Nguyen}}, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_emnlp_howto_gibbs.pdf}{Sometimes Average is Best: The Importance of Averaging for Prediction using MCMC Inference in Topic Modeling}}. \emph{Empirical Methods in Natural Language Processing}, 2014, 6 pages (30\% Acceptance Rate). \item \underline{\href{https://www.ursinus.edu/live/profiles/3125-alvin-grissom-ii}{Alvin Grissom II}}, \underline{\href{https://hhexiy.github.io/}{He He}}, {\bf Jordan Boyd-Graber}, John Morgan, and Hal {Daum\'{e} III}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_emnlp_simtrans.pdf}{Don't Until the Final Verb Wait: Reinforcement Learning for Simultaneous Machine Translation}}. \emph{Empirical Methods in Natural Language Processing}, 2014, 11 pages (30\% Acceptance Rate). \item \underline{\href{https://people.cs.umass.edu/~miyyer/}{Mohit Iyyer}}, {\bf Jordan Boyd-Graber}, Leonardo Claudino, Richard Socher, and Hal {Daum\'{e} III}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_emnlp_qb_rnn.pdf}{A Neural Network for Factoid Question Answering over Paragraphs}}. \emph{Empirical Methods in Natural Language Processing}, 2014, 12 pages (26\% Acceptance Rate). \item \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}}, \underline{\href{https://kzhai.github.io/}{Ke Zhai}}, Vlad Eidelman, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_acl_ptlda_mt.pdf}{Polylingual Tree-Based Topic Models for Translation Domain Adaptation}}. \emph{Association for Computational Linguistics}, 2014, 11 pages (26\% Acceptance Rate). \item \underline{\href{https://people.cs.umass.edu/~miyyer/}{Mohit Iyyer}}, Peter Enns, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_acl_rnn_ideology.pdf}{Political Ideology Detection Using Recursive Neural Networks}}. \emph{Association for Computational Linguistics}, 2014, 10 pages (26\% Acceptance Rate). \item \underline{\href{http://www.umiacs.umd.edu/~daithang/}{Thang Nguyen}}, \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}}, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2014_acl_anchor_reg.pdf}{Anchors Regularized: Adding Robustness and Extensibility to Scalable Topic-Modeling Algorithms}}. \emph{Association for Computational Linguistics}, 2014, 10 pages (26\% Acceptance Rate). \item \underline{\href{http://alisonmsmith.github.io/}{Alison Smith}}, Jason Chuang, \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}}, {\bf Jordan Boyd-Graber}, and Leah Findlater. {\bf Concurrent Visualization of Relationships between Words and Topics in Topic Models}. \emph{ACL Workshop on Workshop on Interactive Language Learning, Visualization, and Interfaces}, 2014. \item Naho Orita, Naomi Feldman, and {\bf Jordan Boyd-Graber}. {\bf Quantifying the role of discourse topicality in speakers' choices of referring expressions}. \emph{ACL Workshop on Cognitive Modeling and Computational Linguistics}, 2014. \end{enumerate} } \headedsection{{\bf 2013}}{}{ \begin{enumerate} \item Naho Orita, Rebecca McKeown, Naomi H. Feldman, Jeffrey Lidz, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2013_cogsci_pronoun.pdf}{Discovering Pronoun Categories using Discourse Information}}. \emph{Proceedings of the Cognitive Science Society}, 2013, 6 pages. \item \underline{\href{http://www.cs.umd.edu/~vietan/index.htm}{Viet-An Nguyen}}, \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}}, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2013_argviz.pdf}{Argviz: Interactive Visualization of Topic Dynamics in Multi-party Conversations}}. \emph{North American Association for Computational Linguistics}, 2013, 4 pages (50\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~vietan/index.htm}{Viet-An Nguyen}}, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2013_shlda.pdf}{Lexical and Hierarchical Topic Regression}}. \emph{Neural Information Processing Systems}, 2013, 10 pages (25\% Acceptance Rate). \item \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}}, {\bf Jordan Boyd-Graber}, Hal {Daum\'{e} III}, and Z. Irene Ying. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2013_coalescent.pdf}{Binary to Bushy: Bayesian Hierarchical Clustering with the Beta Coalescent}}. \emph{Neural Information Processing Systems}, 2013, 9 pages (25\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~vietan/index.htm}{Viet-An Nguyen}}, {\bf Jordan Boyd-Graber}, Jonathan Chang, and Philip Resnik. {\bf Tree-Based Label Dependency Topic Models}. \emph{NIPS Workshop on Topic Models: Computation, Application, and Evaluation}, 2013. \item \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}}, \underline{\href{https://kzhai.github.io/}{Ke Zhai}}, Vlad Edelman, and {\bf Jordan Boyd-Graber}. {\bf Topic Models for Translation Domain Adaptation}. \emph{NIPS Workshop on Topic Models: Computation, Application, and Evaluation}, 2013. \item Thang Nguyen, \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}}, and {\bf Jordan Boyd-Graber}. {\bf Evaluating Regularized Anchor Words}. \emph{NIPS Workshop on Topic Models: Computation, Application, and Evaluation}, 2013. \item \underline{\href{http://www.cs.umd.edu/~vietan/index.htm}{Viet-An Nguyen}}, {\bf Jordan Boyd-Graber}, and Stephen Altschul. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2013_dp_protein.pdf}{Dirichlet Mixtures, the Dirichlet Process, and the Structure of Protein Space}}. \emph{Journal of Computational Biology}, 2013, 48 pages. \item \underline{\href{https://kzhai.github.io/}{Ke Zhai}} and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2013_icml_infvoc.pdf}{Online Topic Models with Infinite Vocabulary}}. \emph{International Conference on Machine Learning}, 2013, 9 pages (20\% Acceptance Rate). \item {\bf Jordan Boyd-Graber}, \underline{Kimberly Glasgow}, and Jackie Sauter Zajac. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2013_spoiler.pdf}{Spoiler Alert: Machine Learning Approaches to Detect Social Media Posts with Revelatory Information}}. \emph{ASIST 2013: The 76th Annual Meeting of the American Society for Information Science and Technology}, 2013, 9 pages. \end{enumerate} } \headedsection{{\bf 2012}}{}{ \begin{enumerate} \item Asad B. Sayeed, {\bf Jordan Boyd-Graber}, Bryan Rusk, and Amy Weinberg. {\bf \href{http://umiacs.umd.edu/~jbg//docs/srt_naacl_2012.pdf}{Grammatical structures for word-level sentiment detection}}. \emph{North American Association for Computational Linguistics}, 2012, 10 pages (31\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~vietan/index.htm}{Viet-An Nguyen}}, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf ``I Want to Talk About, Again, My Record On Energy~\dots'': Modeling Topic Control in Conversations using Speaker-centric Nonparametric Topic Models}. \emph{Mid-Atlantic Student Colloquium on Speech, Language, and Learning}, 2012. \item \underline{\href{https://kzhai.github.io/}{Ke Zhai}} and {\bf Jordan Boyd-Graber}. {\bf Online Topic Model with Infinite Vocabulary}. \emph{Mid-Atlantic Student Colloquium on Speech, Language, and Learning}, 2012. \item \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}} and {\bf Jordan Boyd-Graber}. {\bf Bayesian Hierarchical Clustering with Beta Coalescents}. \emph{Mid-Atlantic Student Colloquium on Speech, Language, and Learning}, 2012. \item \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}}, \underline{\href{https://kzhai.github.io/}{Ke Zhai}}, Sinead Williamson, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/mtibp_icml_2012.pdf}{Modeling Images using Transformed {I}ndian Buffet Processes}}. \emph{International Conference on Machine Learning}, 2012, 8 pages (27\% Acceptance Rate). \item \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}} and {\bf Jordan Boyd-Graber}. {\bf Suggesting Constraints for Interactive Topic Modeling}. \emph{ICML Workshop on Machine Learning in Human Computation and Crowdsourcing}, 2012. \item {\bf Jordan Boyd-Graber}, \underline{Brianna Satinoff}, \underline{\href{https://hhexiy.github.io/}{He He}}, and Hal {Daum\'{e} III}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/qb_emnlp_2012.pdf}{Besting the Quiz Master: Crowdsourcing Incremental Classification Games}}. \emph{Empirical Methods in Natural Language Processing}, 2012, 12 pages (25\% Acceptance Rate). \item \underline{\href{http://www.cs.umd.edu/~vietan/index.htm}{Viet-An Nguyen}}, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/acl_2012_sits.pdf}{{SITS}: A Hierarchical Nonparametric Model using Speaker Identity for Topic Segmentation in Multiparty Conversations}}. \emph{Association for Computational Linguistics}, 2012, 10 pages (19\% Acceptance Rate). \item Vladimir Eidelman, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/acl_2012_tm_for_mt.pdf}{Topic Models for Dynamic Translation Model Adaptation}}. \emph{Association for Computational Linguistics}, 2012, 5 pages (21\% Acceptance Rate). \item \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}} and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/acl_2012_fttm.pdf}{Efficient Tree-Based Topic Modeling}}. \emph{Association for Computational Linguistics}, 2012, 5 pages (21\% Acceptance Rate). \item \underline{\href{https://kzhai.github.io/}{Ke Zhai}}, {\bf Jordan Boyd-Graber}, Nima Asadi, and \underline{Mohamad (Jude) Alkhouja}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2012_www_mrlda.pdf}{{Mr. LDA}: A Flexible Large Scale Topic Modeling Package using Variational Inference in MapReduce}}. \emph{ACM International Conference on World Wide Web}, 2012, 10 pages (12\% Acceptance Rate). \end{enumerate} } \headedsection{{\bf 2011}}{}{ \begin{enumerate} \item Kenneth R. Fleischmann, Clay Templeton, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/iconference-2011-learning.pdf}{Modeling Diverse Standpoints in Text Classification: Learning to Be Human by Modeling Human Values}}. \emph{iConference}, 2011, 2 pages. \item Clay Templeton, Kenneth R. Fleischmann, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/iconference-2011-comparing.pdf}{Comparing Values and Sentiment Using Mechanical Turk}}. \emph{iConference}, 2011, 2 pages. \item \underline{Brianna Satinoff} and {\bf Jordan Boyd-Graber}. {\bf Trivial Classification: What features do humans use for classification?}. \emph{Workshop on Crowdsourcing Technologies for Language and Cognition Studies}, 2011. \item Pranav Anand, Joseph King, {\bf Jordan Boyd-Graber}, Earl Wagner, Craig Martell, Douglas W. Oard, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/persuasion.pdf}{Believe Me: We Can Do This!}}. \emph{The AAAI 2011 workshop on Computational Models of Natural Argument}, 2011, 5 pages. \item {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2011_resources.pdf}{Linguistic Resource Creation in a Web 2.0 World}}. \emph{NSF Workshop on Collaborative Annotation}, 2011, 7 pages. \item Sonya S. Nikolova, {\bf Jordan Boyd-Graber}, and Christiane Fellbaum. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2011_book_chapter_evocation.pdf}{Collecting Semantic Similarity Ratings to Connect Concepts in Assistive Communication Tools}}. \emph{Modeling, Learning and Processing of Text Technological Data Structures}, 2011, 11 pages. \item Clay Templeton, Kenneth R. Fleischmann, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/simulating_audiences.pdf}{Simulating Audiences: Automating Analysis of Values, Attitudes, and Sentiment}}. \emph{IEEE International Conference on Social Computing}, 2011, 4 pages (10\% Acceptance Rate). \item Clay Templeton, Travis Brown, Sayan Battacharyya, and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/slda_civil_war.pdf}{Mining the Dispatch under Supervision: Using Casualty Counts to Guide Topics from the Richmond Daily Dispatch Corpus}}. \emph{Chicago Colloquium on Digital Humanities and Computer Science}, 2011, 7 pages. \item \underline{\href{https://scholar.google.com/citations?user=mO_62fQAAAAJ&hl=en}{Yuening Hu}}, {\bf Jordan Boyd-Graber}, and \underline{Brianna Satinoff}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/itm.pdf}{Interactive Topic Modeling}}. \emph{Association for Computational Linguistics}, 2011, 10 pages (25\% Acceptance Rate). \end{enumerate} } \headedsection{{\bf 2010}}{}{ \begin{enumerate} \item \underline{Eric Hardisty}, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/adapted_naive_bayes.pdf}{Modeling Perspective using Adaptor Grammars}}. \emph{Empirical Methods in Natural Language Processing}, 2010, 10 pages (25\% Acceptance Rate). \item {\bf Jordan Boyd-Graber} and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/jbg-mlslda-2010.pdf}{Holistic Sentiment Analysis Across Languages: Multilingual Supervised Latent Dirichlet Allocation}}. \emph{Empirical Methods in Natural Language Processing}, 2010, 11 pages (25\% Acceptance Rate). \item Nitin Madnani, {\bf Jordan Boyd-Graber}, and Philip Resnik. {\bf \href{http://umiacs.umd.edu/~jbg//docs/madnani-boyd-graber-turk-workshop.pdf}{Measuring Transitivity Using Untrained Annotators}}. \emph{Creating Speech and Language Data With Amazon's Mechanical Turk}, 2010, 6 pages. \item {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/2010_jbg_thesis.pdf}{Linguistic Extensions of Topic Models}}. 2010, 142 pages. \end{enumerate} } \headedsection{{\bf 2009}}{}{ \begin{enumerate} \item {\bf Jordan Boyd-Graber} and David M. Blei. {\bf \href{http://umiacs.umd.edu/~jbg//docs/uai2009.pdf}{Multilingual Topic Models for Unaligned Text}}. \emph{Uncertainty in Artificial Intelligence}, 2009, 8 pages (31\% Acceptance Rate). \item Sonya S. Nikolova, {\bf Jordan Boyd-Graber}, and Perry Cook. {\bf \href{http://umiacs.umd.edu/~jbg//docs/viva.pdf}{The Design of ViVA: A Mixed-initiative Visual Vocabulary for Aphasia}}. \emph{Proceedings of the 27th international conference extended abstracts on Human factors in computing systems}, 2009, 6 pages. \item Jonathan Chang, {\bf Jordan Boyd-Graber}, Chong Wang, Sean Gerrish, and David M. Blei. {\bf \href{http://umiacs.umd.edu/~jbg//docs/nips2009-rtl.pdf}{Reading Tea Leaves: How Humans Interpret Topic Models}}. \emph{Neural Information Processing Systems}, 2009, 9 pages (24\% Acceptance Rate). \item Jonathan Chang, {\bf Jordan Boyd-Graber}, and David M. Blei. {\bf \href{http://umiacs.umd.edu/~jbg//docs/kdd2009.pdf}{Connections between the Lines: Augmenting Social Networks with Text}}. \emph{Knowledge Discovery and Data Mining}, 2009, 9 pages (9\% Acceptance Rate). \item Xiaojuan Ma, {\bf Jordan Boyd-Graber}, Sonya S. Nikolova, and Perry Cook. {\bf \href{http://umiacs.umd.edu/~jbg//docs/image_icon.pdf}{Speaking Through Pictures: Images vs. Icons}}. \emph{ACM Conference on Computers and Accessibility}, 2009, 8 pages (31\% Acceptance Rate). \item Sonya S. Nikolova, {\bf Jordan Boyd-Graber}, Christiane Fellbaum, and Perry Cook. {\bf \href{http://umiacs.umd.edu/~jbg//docs/evocation-viva.pdf}{Better Vocabularies for Assistive Communication Aids: Connecting Terms using Semantic Networks and Untrained Annotators}}. \emph{ACM Conference on Computers and Accessibility}, 2009, 8 pages (31\% Acceptance Rate). \end{enumerate} } \headedsection{{\bf 2008}}{}{ \begin{enumerate} \item {\bf Jordan Boyd-Graber} and David M. Blei. {\bf \href{http://umiacs.umd.edu/~jbg//docs/nips2008.pdf}{Syntactic Topic Models}}. \emph{Neural Information Processing Systems}, 2008, 8 pages (25\% Acceptance Rate). \item {\bf Jordan Boyd-Graber} and David M. Blei. {\bf Multilingual Topic Models}. \emph{NIPS Workshop on Unsupervised Latent Variable Models}, 2008. \item Jonathan Chang, {\bf Jordan Boyd-Graber}, and David M. Blei. {\bf Discovering social networks from free text}. \emph{3rd Annual Machine Learning Symposium}, 2008. \end{enumerate} } \headedsection{{\bf 2007}}{}{ \begin{enumerate} \item {\bf Jordan Boyd-Graber}, David M. Blei, and Xiaojin Zhu. {\bf \href{http://umiacs.umd.edu/~jbg//docs/jbg-EMNLP07.pdf}{A Topic Model for Word Sense Disambiguation}}. \emph{Empirical Methods in Natural Language Processing}, 2007, 10 pages (27\% Acceptance Rate). \item {\bf Jordan Boyd-Graber} and David M. Blei. {\bf \href{http://umiacs.umd.edu/~jbg//docs/jbg-SEMEVAL07.pdf}{{PUTOP}: {T}urning Predominant Senses into a Topic Model for {WSD}}}. \emph{4th International Workshop on Semantic Evaluations}, 2007, 5 pages. \end{enumerate} } \headedsection{{\bf 2006}}{}{ \begin{enumerate} \item {\bf Jordan Boyd-Graber}, Christiane Fellbaum, Daniel Osherson, and Robert Schapire. {\bf \href{http://umiacs.umd.edu/~jbg//docs/jbg-jeju.pdf}{Adding Dense, Weighted, Connections to {WordNet}}}. \emph{Proceedings of the Global {WordNet} Conference}, 2006, 10 pages. \item {\bf Jordan Boyd-Graber}, Sonya S. Nikolova, Karyn A. Moffatt, Kenrick C. Kin, Joshua Y. Lee, Lester W. Mackey, Marilyn M. Tremaine, and Maria M. Klawe. {\bf \href{http://umiacs.umd.edu/~jbg//docs/paper673-boyd-graber.pdf}{Participatory design with proxies: {D}eveloping a desktop-{PDA} system to support people with aphasia}}. \emph{Computer-Human Interaction}, 2006, 10 pages (23\% Acceptance Rate). \end{enumerate} } \headedsection{{\bf 2003}}{}{ \begin{enumerate} \item Alexander Geyken and {\bf Jordan Boyd-Graber}. {\bf \href{http://umiacs.umd.edu/~jbg//docs/idioms.pdf}{Automatic classification of multi-word expressions in print dictionaries}}. \emph{Linguisticae Investigationes}, 2003, 16 pages. \end{enumerate} }