Abstract
We introduce fastcoref, a python package for fast, accurate, and easy-to-use English coreference resolution. The package is pip-installable, and allows two modes: an accurate mode based on the LingMess architecture, providing state-of-the-art coreference accuracy, and a substantially faster model, F-coref, which is the focus of this work. F-coref allows to process 2.8K OntoNotes documents in 25 seconds on a V100 GPU (compared to 6 minutes for the LingMess model, and to 12 minutes of the popular AllenNLP coreference model) with only a modest drop in accuracy. The fast speed is achieved through a combination of distillation of a compact model from the LingMess model, and an efficient batching implementation using a technique we call leftover batching. https://github.com/shon-otmazgin/fastcoref- Anthology ID:
- 2022.aacl-demo.6
- Volume:
- Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations
- Month:
- November
- Year:
- 2022
- Address:
- Taipei, Taiwan
- Venues:
- AACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 48–56
- Language:
- URL:
- https://aclanthology.org/2022.aacl-demo.6
- DOI:
- Cite (ACL):
- Shon Otmazgin, Arie Cattan, and Yoav Goldberg. 2022. F-coref: Fast, Accurate and Easy to Use Coreference Resolution. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations, pages 48–56, Taipei, Taiwan. Association for Computational Linguistics.
- Cite (Informal):
- F-coref: Fast, Accurate and Easy to Use Coreference Resolution (Otmazgin et al., AACL-IJCNLP 2022)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2022.aacl-demo.6.pdf