Abstract
The introduction of pretrained language models has reduced many complex task-specific NLP models to simple lightweight layers. An exception to this trend is coreference resolution, where a sophisticated task-specific model is appended to a pretrained transformer encoder. While highly effective, the model has a very large memory footprint – primarily due to dynamically-constructed span and span-pair representations – which hinders the processing of complete documents and the ability to train on multiple instances in a single batch. We introduce a lightweight end-to-end coreference model that removes the dependency on span representations, handcrafted features, and heuristics. Our model performs competitively with the current standard model, while being simpler and more efficient.- Anthology ID:
- 2021.acl-short.3
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 14–19
- Language:
- URL:
- https://aclanthology.org/2021.acl-short.3
- DOI:
- 10.18653/v1/2021.acl-short.3
- Cite (ACL):
- Yuval Kirstain, Ori Ram, and Omer Levy. 2021. Coreference Resolution without Span Representations. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 14–19, Online. Association for Computational Linguistics.
- Cite (Informal):
- Coreference Resolution without Span Representations (Kirstain et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2021.acl-short.3.pdf
- Code
- yuvalkirstain/s2e-coref
- Data
- CoNLL, CoNLL-2012, GAP Coreference Dataset