PhD student in Natural Language Processing
Lattice (CNRS, ENS-PSL, Université Sorbonne Nouvelle)
I work on coreference resolution and the computational analysis of French literature.
My research looks at how to track characters across entire novels. Most coreference systems are built for short documents, so I build models and annotated corpora for book-length French fiction, then use the output for literary questions such as character gender and narrative structure.
A Natural Language Processing framework for narrative analysis. Includes the trained French coreference pipeline, available as the open-source propp_fr Python library.
Proceedings of the 2nd Joint Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences and Computational Models of Reference, Anaphora and Coreference (CODI-CRAC 2026), San Diego, California, USA.
ArticleJournal of Computational Humanities Research, 2026, 1–15.
ArticleAnthology of Computers and the Humanities, Vol. 3, 2025, pp. 983–999.
ArticleProceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC 2025), EMNLP 2025, Suzhou, China.
PDF arXiv HAL PosterProceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC 2025), EMNLP 2025, Suzhou, China.
PDF Presentation SlidesSéminaire « Interprétations artificielles », CSLF et MSH Mondes, 20 mars 2025.
antoine [dot] bourgois [at] protonmail [dot] com