I am an associate professor in the University of Maryland Computer Science Department (tenure home), Institute of Advanced Computer Studies, iSchool, and Language Science Center. Previously, I was an assistant professor at Colorado's Department of Computer Science (tenure granted in 2017). I was a graduate student at Princeton with David Blei.

My research focuses on making machine learning more useful, more interpretable, and able to learn and interact from humans. This helps users sift through decades of documents; discover when individuals lie, reframe, or change the topic in a conversation; or to compete against humans in games that are based in natural language.

Sign up for an appointment

Recent Publications

  • Chen Zhao, Chenyan Xiong, Hal Daumé III, and Jordan Boyd-Graber. Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval. North American Association of Computational Linguistics, 2021. [Paper Read Aloud] [Bibtex]
  • Julian Martin Eisenschlos, Bhuwan Dhingra, Jannis Bulian, Benjamin Börschinger, and Jordan Boyd-Graber. Fool Me Twice: Entailment from Wikipedia Gamification. North American Association of Computational Linguistics, 2021. [Preprint] [Research Talk] [Code and Data] [Paper Read Aloud] [Play] [Bibtex]
  • Denis Peskov, Viktor Hangya, Jordan Boyd-Graber, and Alexander Fraser. Adapting Entities across Languages and Cultures. Findings of Emperical Methods in Natural Language Processing, 2021. [Bibtex]
  • Chenglei Si, Chen Zhao, and Jordan Boyd-Graber. What's in a Name? Answer Equivalence For Open-Domain Question Answering. Emperical Methods in Natural Language Processing, 2021. [Bibtex]
  • Maharshi Gor, Kellie Webster, and Jordan Boyd-Graber. Toward Deconfounding the Influence of Subject's Demographic Characteristics in Question Answering. Emperical Methods in Natural Language Processing, 2021. [Bibtex]
  • Pedro Rodriguez and Jordan Boyd-Graber. Evaluation Paradigms in Question Answering. Emperical Methods in Natural Language Processing, 2021. [Bibtex]
  • Chen Zhao, Chenyan Xiong, Jordan Boyd-Graber, and Hal Daumé III. Distantly-Supervised Dense Retrieval Enables Open-Domain Question Answering without Evidence Annotation. Emperical Methods in Natural Language Processing, 2021. [Code] [Bibtex]
  • Pedro Rodriguez, Joe Barrow, Alexander Hoyle, John P. Lalor, Robin Jia, and Jordan Boyd-Graber. Evaluation Examples Are Not Equally Informative: How Should That Change NLP Leaderboards?. Association of Computational Linguistics, 2021. [Results and Code] [Paper Read Aloud] [Research Talk Video] [Code and Data] [Bibtex]
  • Alexander Hoyle, Pranav Goel, Denis Peskov, Andrew Hian-Cheong, Jordan Boyd-Graber, and Philip Resnik. Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence. ArXiv, Preprint. [Preprint] [Bibtex]
  • Benjamin Börschinger, Jordan Boyd-Graber, Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Michelle Chen Huebscher, Wojciech Gajewski, Yannic Kilcher, Rodrigo Nogueira, and Lierni Sestorain Saralegu. Meta Answering for Machine Reading. ArXiv, Preprint. [Preprint] [Bibtex]
  • Pedro Rodriguez, Shi Feng, Mohit Iyyer, He He, and Jordan Boyd-Graber. Quizbowl: The Case for Incremental Question Answering. ArXiv, Preprint. [Webpage] [Bibtex]
Jordan Boyd-Graber