Abstract
Academic neural models for coreference resolution (coref) are typically trained on a single dataset, OntoNotes, and model improvements are benchmarked on that same dataset. However, real-world applications of coref depend on the annotation guidelines and the domain of the target dataset, which often differ from those of OntoNotes. We aim to quantify transferability of coref models based on the number of annotated documents available in the target dataset. We examine eleven target datasets and find that continued training is consistently effective and especially beneficial when there are few target documents. We establish new benchmarks across several datasets, including state-of-the-art results on PreCo.- Anthology ID:
- 2021.emnlp-main.425
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5241–5256
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.425
- DOI:
- 10.18653/v1/2021.emnlp-main.425
- Cite (ACL):
- Patrick Xia and Benjamin Van Durme. 2021. Moving on from OntoNotes: Coreference Resolution Model Transfer. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5241–5256, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Moving on from OntoNotes: Coreference Resolution Model Transfer (Xia & Van Durme, EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2021.emnlp-main.425.pdf
- Code
- additional community code
- Data
- GAP Coreference Dataset, PreCo