Steven Bethard

Interests

Research

Natural language processing (NLP) and machine learning (ML) theory and applications, including modeling the language of time and timelines, normalizing text to medical and geospatial ontologies, and information extraction models for clinical applications.

Teaching

Natural language processing (NLP), machine learning (ML), neural networks (NN), information retrieval (IR), artificial intelligence (AI).

Courses

Scholarly Contributions

Books

• Duh, K., Gomez, H., & Bethard, S. J. (2024). Findings of the Association for Computational Linguistics: NAACL 2024. Association for Computational Linguistics.
• Duh, K., Gomez, H., & Bethard, S. J. (2024). Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). Association for Computational Linguistics.
• Duh, K., Gomez, H., & Bethard, S. J. (2024). Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers). Association for Computational Linguistics.
• Naumann, T., Ben Abacha, A., Bethard, S. J., Roberts, K., & Bitterman, D. (2024). Proceedings of the 6th Clinical Natural Language Processing Workshop. Association for Computational Linguistics.
• Naumann, T., Ben Abacha, A., Bethard, S. J., Roberts, K., & Rumshisky, A. (2023). Proceedings of the 5th Clinical Natural Language Processing Workshop. Association for Computational Linguistics.
• Naumann, T., Bethard, S. J., Roberts, K., & Rumshisky, A. (2022). Proceedings of the 4th Clinical Natural Language Processing Workshop. Association for Computational Linguistics.
• Toutanova, K., Rumshisky, A., Zettlemoyer, L., Hakkani-Tur, D., Beltagy, I., Bethard, S. J., Cotterell, R., Chakraborty, T., & Zhou, Y. (2021). Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics.
• Rumshisky, A., Roberts, K., Bethard, S. J., & Naumann, T. (2020). Proceedings of the 3rd Clinical Natural Language Processing Workshop. Association for Computational Linguistics.
• Rumshisky, A., Roberts, K., Bethard, S. J., & Naumann, T. (2019). Proceedings of the 2nd Clinical Natural Language Processing Workshop. Association for Computational Linguistics.
• Apidianaki, M., Mohammad, S. M., May, J., Shutova, E., Bethard, S. J., & Carpuat, M. (2018). Proceedings of The 12th International Workshop on Semantic Evaluation (SemEval-2018). Association for Computational Linguistics.
• Bethard, S. J., Carpuat, M., Apidianaki, M., Mohammad, S. M., Cer, D., & Jurgens, D. (2017). Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017). Association for Computational Linguistics.
• Bethard, S. J., Carpuat, M., Cer, D., Jurgens, D., & Nakov, P. (2016). Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). Association for Computational Linguistics.
• Rumshisky, A., Roberts, K., Bethard, S. J., & Naumann, T. (2016). Proceedings of the Clinical Natural Language Processing Workshop (ClinicalNLP). The COLING 2016 Organizing Committee.
• Kolomiyets, O., Moens, M., Palmer, M., Pustejovsky, J., & Bethard, S. J. (2014). Proceedings of the EACL 2014 Workshop on Computational Approaches to Causality in Language (CAtoCL). Association for Computational Linguistics.
• Bethard, S. J. (2013). 51st Annual Meeting of the Association for Computational Linguistics Proceedings of the Student Research Workshop. Association for Computational Linguistics.
• Bethard, S. J. (2013). Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
• Bethard, S., Jurafsky, D., & Martin, J. H. (2008). Instructor's Solution Manual for Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition (Second Edition). Prentice Hall.

Chapters

• Bethard, S. (2024). Machine Learning and Deep Learning Algorithms. In Natural Language Processing in Biomedicine: A Practical Guide(pp 43--76). Springer International Publishing.
• González López, S., Bethard, S., & López-López, A. (2014). Identifying Weak Sentences in Student Drafts: A Tutoring System. In Methodologies and Intelligent Systems for Technology Enhanced Learning(pp 77-85). Springer International Publishing.
• Bethard, S., Yu, H., Thornton, A., Hatzivassiloglou, V., & Jurafsky, D. (2005). Extracting opinion propositions and opinion holders using syntactic and lexical cues. In Computing Attitude and Affect in Text: Theory and Applications(pp 125--141). Springer.

Journals/Publications

• Barbati, J. L., Rains, S. A., Kenski, K., Shmargad, Y., Bethard, S., & Coe, K. (2024). Examining the Dynamics of Uncivil Discourse Between Sub-National Political Officials and the Public on Twitter. Mass Communication and Society, 0(0), 1-20.
• Zhang, Z., & Bethard, S. (2024). A survey on geocoding: algorithms and datasets for toponym resolution. Language Resources and Evaluation.
• Laparra, E., Binford-Walsh, A., Emerson, K., Miller, M. L., López-Hoffman, L., Currim, F., & Bethard, S. (2023). Addressing structural hurdles for metadata extraction from environmental impact statements. Journal of the Association for Information Science and Technology, 74(9), 1124--1139.
• Rains, S. A., Kenski, K., Dajches, L., Duncan, K., Yan, K., Shin, Y., Barbati, J. L., Bethard, S., Coe, K., & Shmargad, Y. (2023). Engagement with incivility in tweets from and directed at local elected officials. Communication and Democracy, 57(1), 143-152.
• Shmargad, Y., Coe, K., Bethard, S. J., Barbati, J. L., Shin, Y., Yan, K., Duncan, K., Dajches, L., Kenski, K. M., & Rains, S. A. (2023). Engagement with incivility in tweets from and directed at local elected officials. Communication and Democracy.
• Bethard, S. J., Coe, K., Kenski, K. M., Kenski, K. M., Shmargad, Y., Harwood, J. T., & Rains, S. A. (2022). Engagement with partisan Russian troll tweets during the 2016 U.S. presidential election: a social identity perspective. Journal of Communication.
• Lopez Hoffman, L., Lopez Hoffman, L., Miller, M. L., Miller, M. L., Ram, S., Ram, S., Bethard, S. J., Bethard, S. J., Currim, F., Currim, F., Lien, A., Lien, A., Pidot, J. R., Pidot, J. R., Scott, T. A., Scott, T. A., Baldwin, E., Baldwin, E., Emerson, K., & Emerson, K. (2020). NEPA performance: A framework for assessing EIAs. Environmental Impact Assessment Review.
• Lopez Hoffman, L., Miller, M. L., Ram, S., Bethard, S. J., Currim, F., Lien, A., Pidot, J. R., Scott, T., Baldwin, E., & Emerson, K. (2022). Toward NEPA Performance: A framework for assessing EIAs. Environmental Impacts Assessment Review.
• González-López, S., Bethard, S., Orozco, F., & López-Monroy, A. P. (2021). Consumer Cynicism Identification for Spanish Reviews using a Spanish Transformer Model. Procesamiento del Lenguaje Natural, 66(0), 111--120.
• Rains, S. A., Shmargad, Y., Coe, K., Kenski, K., & Bethard, S. (2021). Assessing the Russian Troll Efforts to Sow Discord on Twitter during the 2016 U.S. Election. Human Communication Research, 47(4), 477-486.
• Laparra, E., Bethard, S., & Miller, T. A. (2020). Rethinking domain adaptation for machine learning over clinical language. JAMIA Open.
• Lin, C., Bethard, S., Dligach, D., Sadeque, F., Savova, G., & Miller, T. A. (2020). Does BERT need domain adaptation for clinical negation detection?. Journal of the American Medical Informatics Association, 27(4), 584-591.
• Xu, D., Gopale, M., Zhang, J., Brown, K., Begoli, E., & Bethard, S. (2020). Unified Medical Language System resources improve sieve-based generation and Bidirectional Encoder Representations from Transformers (BERT)–based ranking for concept normalization. Journal of the American Medical Informatics Association.
• González López, S., Bethard, S. J., López-López, A., & Gorrostieta, J. (2019). A Model for Identifying Steps in Undergraduate Thesis Methodology. Research in Computing Science, 148(5), 17--24.
• Laparra, E., Xu, D., & Bethard, S. (2018). From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations. Transactions of the Association for Computational Linguistics, 6, 343--356.
• Osborne, J. D., Neu, M. B., Danila, M. I., Solorio, T., & Bethard, S. J. (2018). CUILESS2016: a clinical corpus applying compositional normalization of text mentions. Journal of Biomedical Semantics, 9(1), 2. doi:10.1186/s13326-017-0173-6
• Miller, T., Dligach, D., Bethard, S., Lin, C., & Savova, G. (2017). Towards generalizable entity-centric clinical coreference resolution. Journal of Biomedical Informatics, 69, 251 - 258. doi:https://doi.org/10.1016/j.jbi.2017.04.015
• Lin, C., Dligach, D., Miller, T. A., Bethard, S., & Savova, G. K. (2016). Multilayered temporal modeling for the clinical domain. Journal of the American Medical Informatics Association, 23(2), 387--395.
• Osborne, J. D., Wyatt, M., Westfall, A. O., Willig, J., Bethard, S., & Gordon, G. (2016). Efficient identification of nationally mandated reportable cancer cases using natural language processing and machine learning. Journal of the American Medical Informatics Association.
• Zhang, C., Pradhan, L., & Bethard, S. (2016). Extracting Hierarchy of Coherent User-Concerns to Discover Intricate User Behavior from User Reviews. International Journal of Multimedia Data Engineering and Management, 7(4), 63-80. doi:10.4018/ijmdem.2016100104
  More info

  Intricate user-behaviors can be understood by discovering user interests from their reviews. Topic modeling techniques have been extensively explored to discover latent user interests from user reviews. However, a topic extracted by topic modelling techniques can be a mixture of several quite different concepts and thus less interpretable. In this paper, the authors present a method that uses topic modeling techniques to discover a large number of topics and applies hierarchical clustering to generate a much smaller number of interpretable User-Concerns. These User-Concerns are further compared with topics generated by Latent Dirichlet Allocation LDA and Pachinko Allocation Model PAM and shown to be more coherent and interpretable. The authors cut the linkage tree formed while performing the hierarchical clustering of the User-Concerns, at different levels, and generate a hierarchy of User-Concerns. They also discuss how collaborative filtering based recommendation systems can be enriched by infusing additional user-behavioral knowledge from such hierarchy.
• Moens, M., Do, Q. T., & Bethard, S. (2015). Domain adaptation in semantic role labeling using a neural language model and linguistic resources. IEEE Transactions on Audio, Speech, and Language Processing, 23(11), 1812-1823. doi:10.1109/taslp.2015.2449072
  More info

  We propose a method for adapting Semantic Role Labeling (SRL) systems from a source domain to a target domain by combining a neural language model and linguistic resources to generate additional training examples. We primarily aim to improve the results of Location, Time, Manner and Direction roles. In our methodology, main words of selected predicates and arguments in the source-domain training data are replaced with words from the target domain. The replacement words are generated by a language model and then filtered by several linguistic filters (including Part-Of-Speech (POS), WordNet and Predicate constraints). In experiments on the out-of-domain CoNLL 2009 data, with the Recurrent Neural Network Language Model (RNNLM) and a well-known semantic parser from Lund University, we show enhanced recall and F1 without penalizing precision on the four targeted roles. These results improve the results of the same SRL system without using the language model and the linguistic resources, and are better than the results of the same SRL system that is trained with examples that are enriched with word embeddings. We also demonstrate the importance of using a language model and the vocabulary of the target domain when generating new training examples.
• Mulder, W. D., Bethard, S., & Moens, M. (2015). A survey on the application of recurrent neural networks to statistical language modeling. Computer Speech & Language, 30(1), 61--98.
• Chambers, N., Cassidy, T., McDowell, B., & Bethard, S. (2014). Dense Event Ordering with a Multi-Pass Architecture. Transactions of the Association for Computational Linguistics, 2, 273--284.
• Styler, W. F., Bethard, S., Finan, S., Palmer, M., Pradhan, S., Groen, P. C., Erickson, B., Miller, T., Lin, C., Savova, G., & Pustejovsky, J. (2014). Temporal Annotation in the Clinical Domain. Transactions of the Association for Computational Linguistics, 2, 143--154.
• Sultan, M. A., Bethard, S., & Sumner, T. (2014). Back to Basics for Monolingual Alignment: Exploiting Word Similarity and Contextual Evidence. Transactions of the Association for Computational Linguistics, 2, 219--230.
• Dligach, D., Bethard, S., Becker, L., Miller, T., & Savova, G. K. (2013). Discovering body site and severity modifiers in clinical texts. Journal of the American Medical Informatics Association.
• Pathak, J., Bailey, K. R., Beebe, C. E., Bethard, S., Carrell, D. S., Chen, P. J., Dligach, D., Endle, C. M., Hart, L. A., Haug, P. J., Huff, S. M., Kaggal, V. C., Li, D., Liu, H., Marchant, K., Masanz, J., Miller, T., Oniki, T. A., Palmer, M., , Peterson, K. J., et al. (2013). Normalization and standardization of electronic health records for high-throughput phenotyping: the SHARPn consortium. Journal of the American Medical Informatics Association, 20(e2), e341-e348.
• Wetzler, P., Bethard, S., Leary, H., Butcher, K., Bahreini, S. D., Zhao, J., Martin, J. H., & Sumner, T. (2013). Characterizing and Predicting the Multifaceted Nature of Quality in Educational Web Resources. ACM Transactions on Interactive Intelligent Systems, 3(3), 15:1--15:25.
• Levin, M., Krawczyk, S., Bethard, S., & Jurafsky, D. (2012). Citation-based bootstrapping for large-scale author disambiguation. Journal of the American Society for Information Science and Technology, 63(5), 1030--1047.
• Bethard, S., Lu, Z., Martin, J. H., & Hunter, L. (2008). Semantic Role Labeling for Protein Transport Predicates. BMC Bioinformatics, 9(1), 277.
• Bethard, S., Martin, J. H., & Klingenstein, S. (2007). Finding Temporal Structure in Text: Machine Learning of Syntactic Temporal Relations. International Journal of Semantic Computing (IJSC), 1(4), 441--458.

Proceedings Publications

• Crum, H., & Bethard, S. (2024, jun). hinoki at SemEval-2024 Task 7: Numeral-Aware Headline Generation (English). In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024).
• Rezaei, M., Kwon, Y., Sanayei, R., Singh, A., & Bethard, S. (2024, jun). CLULab-UofA at SemEval-2024 Task 8: Detecting Machine-Generated Text Using Triplet-Loss-Trained Text Similarity and Text Classification. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024).
• Sanayei, R., Singh, A., Rezaei, M., & Bethard, S. (2024, jun). MARiA at SemEval 2024 Task-6: Hallucination Detection Through LLMs, MNLI, and Cosine similarity. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024).
• Song, H., Bethard, S., & Thomer, A. (2024, aug). Metadata Enhancement Using Large Language Models. In Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024).
• Su, X., Le, T., Bethard, S., & Howard, P. (2024, jun). Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers).
• Zhang, Z., Laparra, E., & Bethard, S. (2024, jun). Improving Toponym Resolution by Predicting Attributes to Constrain Geographical Ontology Entries. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers).
• Bilgis, T., Bozdag, N. B., & Bethard, S. (2023, jul). Gallagher at SemEval-2023 Task 5: Tackling Clickbait with Seq2Seq Models. In Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023).
• Bozdag, N. B., Bilgis, T., & Bethard, S. (2023, jul). Arizonans at SemEval-2023 Task 9: Multilingual Tweet Intimacy Analysis with XLM-T. In Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023).
• Gonzalez-Lopez, S., & Bethard, S. (2023, jul). Transformer-based cynical expression detection in a corpus of Spanish YouTube reviews. In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis.
• Miller, T., Bethard, S., Dligach, D., & Savova, G. (2023, jul). End-to-end clinical temporal information extraction with multi-head attention. In The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks.
• Ozler, K. B., & Bethard, S. (2023, jul). clulab at MEDIQA-Chat 2023: Summarization and classification of medical dialogues. In Proceedings of the 5th Clinical Natural Language Processing Workshop.
• Wang, L., Li, Y., Miller, T., Bethard, S., & Savova, G. (2023, jul). Two-Stage Fine-Tuning for Improved Bias and Variance for Large Pretrained Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
• Yao, J., Bethard, S., Wright-Bettner, K., Goldner, E., Harris, D., & Savova, G. (2023, jul). Textual Entailment for Temporal Dependency Graph Parsing. In Proceedings of the 5th Clinical Natural Language Processing Workshop.
• Zhang, Z., & Bethard, S. (2023, jul). Improving Toponym Resolution with Better Candidate Generation, Transformer-based Reranking, and Two-Stage Resolution. In Proceedings of the The 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023).
• Culnan, J., Romero Diaz, D., & Bethard, S. (2022, jul). Exploring transformers and time lag features for predicting changes in mood over time. In Proceedings of the Eighth Workshop on Computational Linguistics and Clinical Psychology.
• Dligach, D., Bethard, S., Miller, T., & Savova, G. (2022, jul). Exploring Text Representations for Generative Temporal Relation Extraction. In Proceedings of the 4th Clinical Natural Language Processing Workshop.
• Song, H., & Bethard, S. (2022, jul). UA-KO at SemEval-2022 Task 11: Data Augmentation and Ensembles for Korean Named Entity Recognition. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022).
• Su, X., Zhao, Y., & Bethard, S. (2022, may). A Comparison of Strategies for Source-Free Domain Adaptation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
• Surdeanu, M., Hungerford, J., Chan, Y. S., MacBride, J., Gyori, B., Zupon, A., Tang, Z., Qiu, H., Min, B., Zverev, Y., Hilverman, C., Thomas, M., Andrews, W., Alcock, K., Zhang, Z., Reynolds, M., Bethard, S., Sharp, R., & Laparra, E. (2022, jul). Taxonomy Builder: a Data-driven and User-centric Tool for Streamlining Taxonomy Construction. In Proceedings of the Second Workshop on Bridging Human--Computer Interaction and Natural Language Processing.
• Tasnim, N., Shihab, M. I., Shahriyar Sushmit, A., Bethard, S., & Sadeque, F. (2022, jul). TEAM-Atreides at SemEval-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in Bangla. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022).
• Wang, L., Miller, T., Bethard, S., & Savova, G. (2022, jul). Ensemble-based Fine-Tuning Strategy for Temporal Relation Extraction from the Clinical Narrative. In Proceedings of the 4th Clinical Natural Language Processing Workshop.
• Bertsch, A., & Bethard, S. (2021, nov). Detection of Puffery on the English Wikipedia. In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021).
• Laparra, E., Su, X., Zhao, Y., Uzuner, Ö., Miller, T., & Bethard, S. (2021, aug). SemEval-2021 Task 10: Source-Free Domain Adaptation for Semantic Processing. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021).
• Liang, Z., Bethard, S., & Surdeanu, M. (2021, jun). Explainable Multi-hop Verbal Reasoning Through Internal Monologue. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
• Lin, C., Miller, T., Dligach, D., Bethard, S., & Savova, G. (2021, jun). EntityBERT: Entity-centric Masking Strategy for Model Pretraining for the Clinical Domain. In Proceedings of the 20th Workshop on Biomedical Language Processing.
• Miller, T., Laparra, E., & Bethard, S. (2021, apr). Domain adaptation in practice: Lessons from a real-world information extraction pipeline. In Proceedings of the Second Workshop on Domain Adaptation for NLP.
• Su, P., & Bethard, S. (2021, nov). Simplifying annotation of intersections in time normalization annotation: exploring syntactic and semantic validation. In Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop.
• Su, X., Zhao, Y., & Bethard, S. (2021, aug). The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021).
• Xu, D., & Bethard, S. (2021, jun). Triplet-Trained Vector Space and Sieve-Based Search Improve Biomedical Concept Normalization. In Proceedings of the 20th Workshop on Biomedical Language Processing.
• Yadav, V., Bethard, S., & Surdeanu, M. (2021, jun). If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
• Zhao, Y., Ngui, J. G., Hall, H. L., & Bethard, S. (2021, nov). Do pretrained transformers infer telicity like humans?. In Proceedings of the 25th Conference on Computational Natural Language Learning.
• Gonz'alez-L'opez, S., Bethard, S., & Lopez-Lopez, A. (2020, jul). Assisting Undergraduate Students in Writing Spanish Methodology Sections. In Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications.
• Kim, M., & Bethard, S. (2020, dec). TTUI at SemEval-2020 Task 11: Propaganda Detection with Transfer Learning and Ensembles. In Proceedings of the Fourteenth Workshop on Semantic Evaluation.
• Laparra, E., & Bethard, S. (2020, dec). A Dataset and Evaluation Framework for Complex Geographical Description Parsing. In Proceedings of the 28th International Conference on Computational Linguistics.
• Lin, C., Miller, T., Dligach, D., Sadeque, F., Bethard, S., & Savova, G. (2020, jul). A BERT-based One-Pass Multi-Task Model for Clinical Temporal Relation Extraction. In Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing.
• Ozler, K. B., Kenski, K., Rains, S., Shmargad, Y., Coe, K., & Bethard, S. (2020, nov). Fine-tuning for multi-domain and multi-label uncivil language detection. In Proceedings of the Fourth Workshop on Online Abuse and Harms.
• Wright-Bettner, K., Lin, C., Miller, T., Bethard, S., Dligach, D., Palmer, M., Martin, J. H., & Savova, G. (2020, nov). Defining and Learning Refined Temporal Relations in the Clinical Narrative. In Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis.
• Xu, D., Zhang, Z., & Bethard, S. (2020, jul). A Generate-and-Rank Framework with Semantic Type Regularization for Biomedical Concept Normalization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.
• Yadav, V., Bethard, S., & Surdeanu, M. (2020, 7). Having Your Cake and Eating It Too: Training Neural Retrieval for Language Inference without Losing Lexical Match. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.
• Yadav, V., Bethard, S., & Surdeanu, M. (2020, jul). Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.
• Zhao, Y., & Bethard, S. (2020, jul). How does BERT's attention change when you fine-tune? An analysis methodology and a case study in negation scope. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.
• Bethard, S., Laparra, E., Wang, S., Zhao, Y., Al-Ghezi, R., Lien, A., & L'opez-Hoffman, L. (2019, 6). Inferring missing metadata from environmental policy texts. In Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature.
• Lin, C., Miller, T., Dligach, D., Bethard, S., & Savova, G. (2019, 6). A BERT-based Universal Model for Both Within- and Cross-sentence Clinical Temporal Relation Extraction. In Proceedings of the 2nd Clinical Natural Language Processing Workshop.
• Sadeque, F., Rains, S., Shmargad, Y., Kenski, K., Coe, K., & Bethard, S. (2019, 6). Incivility Detection in Online Comments. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019).
• Sharp, R., Pyarelal, A., Gyori, B., Alcock, K., Laparra, E., Valenzuela-Escárcega, M. A., Nagesh, A., Yadav, V., Bachman, J., Tang, Z., Lent, H., Luo, F., Paul, M., Bethard, S., Barnard, K., Morrison, C., & Surdeanu, M. (2019, 6). Eidos, INDRA, & Delphi: From Free Text to Executable Causal Models. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations).
• Surdeanu, M., Morrison, C. T., Barnard, J. J., Bethard, S. J., Paul, M., Luo, F., Lent, H., Tang, Z., Bachman, J. A., Yadav, V., Nagesh, A., Valenzuela-Escárcega, M. A., Laparra, E., Alcock, K., Gyori, B. M., Pyarelal, A., & Sharp, R. (2019, Summer). Eidos, INDRA & Delphi: From Free Text to Executable Causal Models. In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL).
• Xu, D., Laparra, E., & Bethard, S. (2019, 6). Pre-trained Contextualized Character Embeddings Lead to Major Improvements in Time Normalization: a Detailed Analysis. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019).
• Yadav, V., Bethard, S., & Surdeanu, M. (2019, 6). Alignment over Heterogeneous Embeddings for Question Answering. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers).
• Yadav, V., Bethard, S., & Surdeanu, M. (2019, nov). Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).
• Yadav, V., Laparra, E., Wang, T., Surdeanu, M., & Bethard, S. (2019, 6). University of Arizona at SemEval-2019 Task 12: Deep-Affix Named Entity Recognition of Geolocation Entities. In Proceedings of the 13th International Workshop on Semantic Evaluation.
• Laparra, E., Xu, D., Elsayed, A., Bethard, S., & Palmer, M. (2018, 6). SemEval 2018 Task 6: Parsing Time Normalizations. In Proceedings of The 12th International Workshop on Semantic Evaluation.
• Lin, C., Miller, T., Dligach, D., Amiri, H., Bethard, S., & Savova, G. (2018, 10). Self-training improves Recurrent Neural Networks performance for Temporal Relation Extraction. In Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis.
• Pradhan, L., Zhang, C., Bethard, S., & Chen, X. (2018, 4). Embedding User Behavioral Aspect in TF-IDF Like Representation. In 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR).
• Sadeque, F., Xu, D., & Bethard, S. (2018, Feb). Measuring the Latency of Depression Detection in Social Media. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining.
• Xu, D., Yadav, V., & Bethard, S. (2018, 5). UArizona at the MADE1.0 NLP Challenge. In Proceedings of the 1st International Workshop on Medication and Adverse Drug Event Detection, 90.
• Yadav, V., & Bethard, S. (2018, 8). A Survey on Recent Advances in Named Entity Recognition from Deep Learning models. In Proceedings of the 27th International Conference on Computational Linguistics.
• Yadav, V., Sharp, R., & Bethard, S. (2018, 6). Deep Affix Features Improve Neural Named Entity Recognizers. In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics.
• Bethard, S., Savova, G., Palmer, M., & Pustejovsky, J. (2017, 8). SemEval-2017 Task 12: Clinical TempEval. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), 565-572.
• Dligach, D., Miller, T., Lin, C., Bethard, S., & Savova, G. (2017, 4). Neural Temporal Relation Extraction. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, 746-751.
• Do, Q., Bethard, S., & Moens, M. (2017, 11). Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 90-99.
• Lin, C., Miller, T., Dligach, D., Bethard, S., & Savova, G. (2017, 8). Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks. In BioNLP 2017, 322-327.
• Miller, T., Bethard, S., Amiri, H., & Savova, G. (2017, 8). Unsupervised Domain Adaptation for Clinical Negation Detection. In BioNLP 2017, 165-170.
• Pradhan, L., Zhang, C., & Bethard, S. (2017, 8). Infusing Latent User-Concerns from User Reviews into Collaborative Filtering. In 2017 IEEE International Conference on Information Reuse and Integration (IRI), 471-477.
• Sadeque, F., Xu, D., & Bethard, S. (2017, 9). UArizona at the CLEF eRisk 2017 Pilot Task: Linear and Recurrent Models for Early Depression Detection. In CEUR workshop proceedings: Working Notes of CLEF 2017 - Conference and Labs of the Evaluation Forum.
• Viani, N., Miller, T. A., Dligach, D., Bethard, S., Napolitano, C., Priori, S. G., Bellazzi, R., Sacchi, L., & Savova, G. K. (2017, June 21-24). Recurrent Neural Network Architectures for Event Extraction from Italian Medical Reports. In Artificial Intelligence in Medicine: 16th Conference on Artificial Intelligence in Medicine (AIME 2017).
• Bethard, S., & Parker, J. (2016, 5). A Semantically Compositional Annotation Scheme for Time Normalization. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).
• Bethard, S., Savova, G., Chen, W., Derczynski, L., Pustejovsky, J., & Verhagen, M. (2016, 6). SemEval-2016 Task 12: Clinical TempEval. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016).
• Do, Q. N., Bethard, S., & Moens, M. (2016, 11). Visualizing the Content of a Children's Story in a Virtual World: Lessons Learned. In Proceedings of the Workshop on Uphill Battles in Language Processing: Scaling Early Achievements to Robust Methods.
• Do, Q. N., Bethard, S., & Moens, M. (2016, 12). Facing the most difficult case of Semantic Role Labeling: A collaboration of word embeddings and co-training. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers.
• Lin, C., Miller, T., Dligach, D., Bethard, S., & Savova, G. (2016, 8). Improving Temporal Relation Extraction with Training Instance Augmentation. In Proceedings of the 15th Workshop on Biomedical Natural Language Processing.
• Rey-Villamizar, N., Shrestha, P., Sadeque, F., Bethard, S., Pedersen, T., Mukherjee, A., & Solorio, T. (2016, 11). Analysis of Anxious Word Usage on Online Health Forums. In Proceedings of the Seventh International Workshop on Health Text Mining and Information Analysis.
• Rey-Villamizar, N., Shrestha, P., Solorio, T., Sadeque, F., Bethard, S., & Pedersen, T. (2016, 6). Semi-supervised CLPsych 2016 Shared Task System Submission. In Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology.
• Sadeque, F., Pedersen, T., Solorio, T., Shrestha, P., Rey-Villamizar, N., & Bethard, S. (2016, 11). Why Do They Leave: Modeling Participation in Online Depression Forums. In Proceedings of The Fourth International Workshop on Natural Language Processing for Social Media.
• Sapkota, U., Solorio, T., Montes, M., & Bethard, S. (2016, 8). Domain Adaptation for Authorship Attribution: Improved Structural Correspondence Learning. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
• Shrestha, P., Rey-Villamizar, N., Sadeque, F., Pedersen, T., Bethard, S., & Solorio, T. (2016, 5). Age and Gender Prediction on Health Forum Data. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).
• Sultan, M. A., Bethard, S., & Sumner, T. (2016, 6). DLS@CU at SemEval-2016 Task 1: Supervised Models of Sentence Similarity. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016).
• Zhang, C., Pradhan, L., & Bethard, S. (2016, 7). Towards Extracting Coherent User Concerns and Their Hierarchical Organization from User Reviews. In 2016 IEEE 17th International Conference on Information Reuse and Integration (IRI), 582-590.
  More info

  Mining user reviews to discover what the user likes and dislikes is vital to understanding user behaviors. Topic modeling techniques have been extensively used to discover meaningful topics for user reviews and to discover user behaviors. Extracted topics may be a mixture of different concepts and hence very likely to be less coherent and unclear, especially when extracting a relatively small number of topics. As such, we propose a method that extracts a relatively large number of topics using a topic modeling technique and relies on hierarchical clustering to exploit semantic distances between topics, to generate a small number of highly coherent and clear topics. We also compare this set of topics representing hidden user concerns extracted by our approach with those derived using LDA (Latent Dirichlet Allocation) and a hierarchical variant called Pachinko Allocation Model (PAM) and show that our method generates more coherent user concerns. Further, we also demonstrate how a hierarchical model of user concerns can be automatically generated by exploiting our approach. Such a hierarchy may help capture the conceptual distances between various user concerns and inherent similarities between users having those concerns.
• Bethard, S., Derczynski, L., Savova, G., Pustejovsky, J., & Verhagen, M. (2015, 6). SemEval-2015 Task 6: Clinical TempEval. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015).
• Do, Q. N., Bethard, S., & Moens, M. (2015, 9). Adapting Coreference Resolution for Narrative Processing. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.
• Gung, J., Osborne, J., & Bethard, S. (2015, 6). CUAB: Supervised Learning of Disorders and their Attributes using Relations. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015).
• Maharjan, S., Blair, E., Bethard, S., & Solorio, T. (2015, 6). Developing Language-tagged Corpora for Code-switching Tweets. In Proceedings of The 9th Linguistic Annotation Workshop.
• Miller, T., Bethard, S., Dligach, D., Lin, C., & Savova, G. (2015, 7). Extracting Time Expressions from Clinical Text. In Proceedings of BioNLP 15.
• Sadeque, F., Solorio, T., Pedersen, T., Shrestha, P., & Bethard, S. (2015, 9). Predicting Continued Participation in Online Health Forums. In Proceedings of the Sixth International Workshop on Health Text Mining and Information Analysis.
• Sapkota, U., Bethard, S., Montes, M., & Solorio, T. (2015, 6). Not All Character N-grams Are Created Equal: A Study in Authorship Attribution. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
• Sultan, M. A., Bethard, S., & Sumner, T. (2015, 6). DLS@CU: Sentence Similarity from Word Alignment and Semantic Vector Composition. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015).
• Sultan, M. A., Bethard, S., & Sumner, T. (2015, 9). Feature-Rich Two-Stage Logistic Regression for Monolingual Alignment. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.
• Bethard, S., Ogren, P., & Becker, L. (2014, 5). ClearTK 2.0: Design Patterns for Machine Learning in UIMA. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14).
• Bursztein, E., Moscicki, A., Fabry, C., Bethard, S., Mitchell, J. C., & Jurafsky, D. (2014, 4). Easy Does It: More Usable CAPTCHAs. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems.
• Cassidy, T., McDowell, B., Chambers, N., & Bethard, S. (2014, 6). An Annotation Framework for Dense Event Ordering. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).
• Do, Q. N., Bethard, S., & Moens, M. (2014, 9). Text Mining for Open Domain Semi-Supervised Semantic Role Labeling. In Proceedings of the 1st International Workshop on Interactions between Data Mining and Natural Language Processing.
• Lin, C., Miller, T., Kho, A., Bethard, S., Dligach, D., Pradhan, S., & Savova, G. (2014, 6). Descending-Path Convolution Kernel for Syntactic Structures. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).
• Manning, C., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S., & McClosky, D. (2014, 6). The Stanford CoreNLP Natural Language Processing Toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations.
• Sapkota, U., Solorio, T., Montes, M., Bethard, S., & Rosso, P. (2014, 8). Cross-Topic Authorship Attribution: Will Out-Of-Topic Data Help?. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers.
• Solorio, T., Blair, E., Maharjan, S., Bethard, S., Diab, M., Ghoneim, M., Hawwari, A., AlGhamdi, F., Hirschberg, J., Chang, A., & Fung, P. (2014, 10). Overview for the First Shared Task on Language Identification in Code-Switched Data. In Proceedings of the First Workshop on Computational Approaches to Code Switching.
• Sultan, M. A., Bethard, S., & Sumner, T. (2014, 8). DLS@CU: Sentence Similarity from Word Alignment. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014).
• Sultan, M. A., Bethard, S., & Sumner, T. (2014, 9). Towards automatic identification of core concepts in educational resources. In 2014 IEEE/ACM Joint Conference on Digital Libraries (JCDL).
• Bethard, S. (2013, 10). A Synchronous Context Free Grammar for Time Normalization. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing.
• Bethard, S. (2013, 6). ClearTK-TimeML: A minimalist approach to TempEval 2013. In Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013).
• Kolomiyets, O., Kordjamshidi, P., Moens, M., & Bethard, S. (2013, 6). SemEval-2013 Task 3: Spatial Role Labeling. In Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013).
• Miller, T., Bethard, S., Dligach, D., Pradhan, S., Lin, C., & Savova, G. (2013, 8). Discovering Temporal Narrative Containers in Clinical Text. In Proceedings of the 2013 Workshop on Biomedical Natural Language Processing.
• Okoye, I., Bethard, S., & Sumner, T. (2013, 6). CU: Computational Assessment of Short Free Text Answers - A Tool for Evaluating Students' Understanding. In Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013).
• Okoye, I., Sumner, T., & Bethard, S. (2013, 7). Automatic extraction of core learning goals and generation of pedagogical sequences through a collection of digital library resources. In Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries.
• Sultan, M. A., Bethard, S., & Sumner, T. (2013, 6). DLS@CU-CORE: A Simple Machine Learning Model of Semantic Textual Similarity. In Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 1: Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarity.
• Bethard, S., Kolomiyets, O., & Moens, M. (2012, 5). Annotating Story Timelines as Temporal Dependency Structures. In Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12).
• Bethard, S., Okoye, I., Sultan, M. A., Hang, H., Martin, J. H., & Sumner, T. (2012, 6). Identifying science concepts and student misconceptions in an interactive essay writing tutor. In Proceedings of the Seventh Workshop on Building Educational Applications Using NLP.
• Jans, B., Bethard, S., Vulić, I., & Moens, M. (2012, 4). Skip N-grams and Ranking Functions for Predicting Script Events. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics.
• Kolomiyets, O., Bethard, S., & Moens, M. (2012, 7). Extracting Narrative Timelines as Temporal Dependency Structures. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
• Kordjamshidi, P., Bethard, S., & Moens, M. (2012, 6). SemEval-2012 Task 3: Spatial Role Labeling. In *SEM 2012: The First Joint Conference on Lexical and Computational Semantics -- Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012).
• Gusev, A., Chambers, N., Khilnani, D. R., Khaitan, P., Bethard, S., & Jurafsky, D. (2011, 1). Using Query Patterns to Learn the Duration of Events. In International Conference on Computational Semantics.
• Kolomiyets, O., Bethard, S., & Moens, M. (2011, 6). Model-Portability Experiments for Textual Temporal Analysis. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies.
• Bethard, S., & Jurafsky, D. (2010, 10). Who Should I Cite? Learning Literature Search Models from Citation Behavior. In ACM Conference on Information and Knowledge Management.
• Bursztein, E., Bethard, S., Mitchell, J. C., Jurafsky, D., & Fabry, C. (2010, 5). How Good are Humans at Solving CAPTCHAs? A Large Scale Evaluation. In IEEE Symposium on Security and Privacy.
• Lai, V. T., & Bethard, S. (2010, 2). Early ERP Effects of the Metaphorical Profile of a Word. In 7th Mental Lexicon Conference.
• Munro, R., Bethard, S., Kuperman, V., Lai, V. T., Melnick, R., Potts, C., Schnoebelen, T., & Tily, H. (2010, 6). Crowdsourcing and language studies: the new generation of linguistic data. In NAACL Workshop on Creating Speech and Language Data With Amazon's Mechanical Turk.
• Bethard, S., Ghosh, S., Martin, J. H., & Sumner, T. (2009, 6). Topic model methods for automatically identifying out-of-scope resources. In JCDL '09: Proceedings of the 9th ACM/IEEE-CS Joint Conference on Digital Libraries.
• Bethard, S., Lai, V. T., & Martin, J. H. (2009, 6). Topic Model Analysis of Metaphor Frequency for Psycholinguistic Stimuli. In Proceedings of the Workshop on Computational Approaches to Linguistic Creativity.
• Bethard, S., Wetzler, P., Butcher, K., Martin, J. H., & Sumner, T. (2009, 6). Automatically characterizing resource quality for educational digital libraries. In JCDL '09: Proceedings of the 9th ACM/IEEE-CS Joint Conference on Digital Libraries.
• Bursztein, E., & Bethard, S. (2009, 8). Decaptcha: Breaking 75\% of eBay Audio CAPTCHAs. In 3rd USENIX Workshop on Offensive Technologies.
• Ogren, P. V., Wetzler, P. G., & Bethard, S. J. (2009, 9). ClearTK: A Framework for Statistical Natural Language Processing. In Unstructured Information Management Architecture Workshop at the Conference of the German Society for Computational Linguistics and Language Technology.
• Ogren, P., & Bethard, S. (2009, 6). Building Test Suites for UIMA Components. In Proceedings of the Workshop on Software Engineering, Testing, and Quality Assurance for Natural Language Processing (SETQA-NLP 2009).
• Savova, G., Bethard, S., Styler, W., Martin, J. H., Palmer, M., Masanz, J., & Ward, W. (2009, 11). Towards Temporal Relation Discovery from the Clinical Narrative. In American Medical Informatics Association Annual Symposium.
• Wetzler, P. G., Bethard, S., Butcher, K., Martin, J. H., & Sumner, T. (2009, 4). Automatically assessing resource quality for educational digital libraries. In WICOW '09: Proceedings of the 3rd workshop on Information credibility on the web.
• Bethard, S., & Martin, J. H. (2008, 6). Learning Semantic Links from a Corpus of Parallel Temporal and Causal Relations. In Proceedings of ACL-08: HLT, Short Papers.
• Bethard, S., Corvey, W., Klingenstein, S., & Martin, J. H. (2008, 5). Building a Corpus of Temporal-Causal Structure. In Language Resources and Evaluation Conference (LREC).
• Ogren, P. V., Wetzler, P. G., & Bethard, S. J. (2008, 5). ClearTK: A UIMA Toolkit for Statistical Natural Language Processing. In UIMA for NLP workshop at Language Resources and Evaluation Conference (LREC).
• Bethard, S., & Martin, J. H. (2007, 6). CU-TMP: Temporal Relation Classification Using Syntactic and Semantic Features. In Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007).
• Bethard, S., Martin, J. H., & Klingenstein, S. (2007, 9). Timelines from Text: Identification of Syntactic Temporal Relations. In International Conference on Semantic Computing (ICSC).
• Bethard, S., Nielsen, R., Martin, J. H., Ward, W., & Palmer, M. (2007, 3). Semantic integration in learning from text. In AAAI Spring Symposium on Machine Reading.
• Bethard, S., & Martin, J. H. (2006, 7). Identification of Event Mentions and their Semantic Class. In Empirical Methods in Natural Language Processing (EMNLP).
• Bethard, S., Yu, H., Thornton, A., Hatzivassiloglou, V., & Jurafsky, D. (2004, 3). Automatic extraction of opinion propositions and their holders. In AAAI Spring Symposium on Exploring Attitude and Affect in Text: Theories and Applications.
• Pradhan, S. S., Illouz, G., Blair-Goldensohn, S. J., Schlaikjer, A. H., Krugler, V., Filatova, E., Duboue, P. A., Yu, H., Passonneau, R. J., Bethard, S., Hatzivassiloglou, V., Ward, W., Jurafsky, D., McKeown, K. R., & Martin, J. H. (2002, 11). Building a foundation system for producing short answers to factual questions. In Text REtrieval Conference (TREC).

Presentations

• Bethard, S. J. (2022, Dec 10). We need to talk about random seeds. Conference on Empirical Methods in Natural Language Processing Birds of a Feather session.
• Bethard, S. J. (2022, Jul 27). Adapting machine learning models for clinical language processing. University of Colorado Boulder Computational Language and Education Research Seminar.
• Bethard, S. J. (2022, Jun 20). Adapting machine learning models for clinical language processing. University of Arizona Computer Science Colloquium.
• Bethard, S. J. (2021, Feb 26). Adapting natural language processing models across clinical domains. University of Alabama at Birmingham Informatics Institute Seminar.
• Lien, A., Ram, S., Miller, M. L., Bethard, S. J., Emerson, K., & Lopez Hoffman, L. (2021). NEPAccess: Bringing NEPA Into the 21st Century Through the Power of Data Science. James E. Rogers College of Law Environmental Breakfast Club.
• Lien, A., Ram, S., Miller, M. L., Bethard, S. J., Emerson, K., & Lopez Hoffman, L. (2021). NEPAccess: Bringing NEPA Into the 21st Century Through the Power of Data Science. University of Arizona Center for Outreach & Collaboration, Washington DC Inaugural Event.
• Bethard, S. J. (2019, Feb 16). Human Annotation and Machine Learning in Understanding the Language of Time. 2019 AAAS Annual MeetingAmerican Association for the Advancement of Science.
• Bethard, S. J. (2018, April 6). Teaching Computers the Language of Time. University of Arizona Cognitive Science Colloquium.
• Bethard, S. J. (2018, March 16). Parsing the Language of Time. University of Arizona Management Information Systems Seminar.

Others

• Bethard, S. (2022, oct). We need to talk about random seeds. https://arxiv.org/abs/2210.13393
• Kim, B., Bethard, S. J., Ram, S., Emerson, K., Pidot, J. R., Miller, M. L., & Lopez Hoffman, L. (2020, June). NEPAccess Senate Letter. Senate Committee on Environment and Public Works.
  More info

  Letter written the US Senate Committee on Environment and Public Works to be considered in a hearing. The letter provided evidence from early research conducted using the NEPAccess platform (under development by our team) related to time required for agencies to produce Environmental Impact Statements.
• Baker, K., Bethard, S., Bloodgood, M., Brown, R., Callison-Burch, C., Coppersmith, G., Dorr, B., Filardo, W., Giles, K., Irvine, A., Kayser, M., Levin, L., Martineau, J., Mayfield, J., Miller, S., Phillips, A., Philpot, A., Piatko, C., Schwartz, L., & Zajic, D. (2010, 1). Semantically Informed Machine Translation (SIMT). https://cs.jhu.edu/~ccb/publications/scale-2009-report.pdf
• Bethard, S. (2007, 12). Finding Event, Temporal and Causal Structure in Text: A Machine Learning Approach. https://www.proquest.com/docview/304860129