• My research interests are in human-centered natural language processing.

    Specifically, I'm interested in the implicit knowledge that NLP models acquire during training (both supervised and unsupervised), and how to extract this knowledge and present it to human stakeholders in ways that let them make more effective and ethical use of those models. I do both algorithmic work, coming up with methods to effectively extract knowledge from models, and human-subject experimentation work to better understand how humans work with those models.
  • Selected Publications

    Academic Article

    Year Title
    2018 Early Intervention Systems: Predicting Adverse Interactions Between Police and the PublicCriminal Justice Policy Review.  29:190-209. 2018


    Year Title
    2022 Learning to Ignore Adversarial Attacks 2022
    2020 Harnessing Explanations to Bridge AI and Humans 2020
    2016 Context-aware Natural Language Generation with Recurrent Neural Networks 2016

    Conference Paper

    Year Title
    2022 What to Learn, and How: Toward Effective Learning from RationalesFindings of the Association for Computational Linguistics: ACL 2022. 2022
    2021 Explainable Prediction of Text Complexity: The Missing Preliminaries for Text SimplificationProceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021
    2020 Evaluating and Characterizing Human RationalesProceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020
    2019 Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review GenerationProceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019
    2018 Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media PostsProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018
    2016 Identifying Police Officers at Risk of Adverse EventsProceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016
    2012 Explanatory semantic relatedness and explicit spatialization for exploratory searchProceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval. 2012
    2012 OmnipediaProceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2012

    Teaching Activities

  • Advanced Topics Taught course
  • Natural Language Processing Taught course
  • Topics Taught course 2023
  • AdvTop/Fair,Accnt&TrnspMchLrn Taught course 2022
  • Education And Training

  • Ph.D. Information Science/Studies, University of Michigan
  • Full Name

  • Samuel Carton