Abstract
Coreference annotation and resolution is a vital component of computational literary studies. However, it has previously been difficult to build high quality systems for fiction. Coreference requires complicated structured outputs, and literary text involves subtle inferences and highly varied language. New language-model-based seq2seq systems present the opportunity to solve both these problems by learning to directly generate a copy of an input sentence with markdown-like annotations. We create, evaluate, and release several trained models for coreference, as well as a workflow for training new models.- Anthology ID:
- 2024.latechclfl-1.27
- Volume:
- Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024)
- Month:
- March
- Year:
- 2024
- Address:
- St. Julians, Malta
- Editors:
- Yuri Bizzoni, Stefania Degaetano-Ortlieb, Anna Kazantseva, Stan Szpakowicz
- Venues:
- LaTeCHCLfL | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 270–277
- Language:
- URL:
- https://aclanthology.org/2024.latechclfl-1.27
- DOI:
- Cite (ACL):
- Rebecca Hicke and David Mimno. 2024. [Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMs. In Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024), pages 270–277, St. Julians, Malta. Association for Computational Linguistics.
- Cite (Informal):
- [Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMs (Hicke & Mimno, LaTeCHCLfL-WS 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.latechclfl-1.27.pdf