Samuel Carton
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.
Courses Taught
- CS 780/880: Topics
- CS 980: AdvTop/Fair,Accnt&TrnspMchLrn
Selected Publications
Carton, S., Kanoria, S., & Tan, C. (2022). What to Learn, and How: Toward Effective Learning from Rationales. In Findings of the Association for Computational Linguistics: ACL 2022. Association for Computational Linguistics. doi:10.18653/v1/2022.findings-acl.86
Garbacea, C., Guo, M., Carton, S., & Mei, Q. (2021). Explainable Prediction of Text Complexity: The Missing Preliminaries for Text Simplification. In Proceedings 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). Association for Computational Linguistics. doi:10.18653/v1/2021.acl-long.88
Carton, S., Rathore, A., & Tan, C. (2020). Evaluating and Characterizing Human Rationales. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics. doi:10.18653/v1/2020.emnlp-main.747
Garbacea, C., Carton, S., Yan, S., & Mei, Q. (2019). Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation. 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). Association for Computational Linguistics. doi:10.18653/v1/d19-1409
Helsby, J., Carton, S., Joseph, K., Mahmud, A., Park, Y., Navarrete, A., . . . Ghani, R. (2018). Early Intervention Systems: Predicting Adverse Interactions Between Police and the Public. Criminal Justice Policy Review, 29(2), 190-209. doi:10.1177/0887403417695380
Carton, S., Mei, Q., & Resnick, P. (2018). Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. doi:10.18653/v1/d18-1386
Carton, S., Helsby, J., Joseph, K., Mahmud, A., Park, Y., Walsh, J., . . . Ghani, R. (2016). Identifying Police Officers at Risk of Adverse Events. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM. doi:10.1145/2939672.2939698
Hecht, B., Carton, S. H., Quaderi, M., Schöning, J., Raubal, M., Gergle, D., & Downey, D. (2012). Explanatory semantic relatedness and explicit spatialization for exploratory search. In Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval. ACM. doi:10.1145/2348283.2348341
Bao, P., Hecht, B., Carton, S., Quaderi, M., Horn, M., & Gergle, D. (2012). Omnipedia. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM. doi:10.1145/2207676.2208553