Coreferential Reasoning Learning for Language Representation
Deming Ye, Yankai Lin, Jiaju Du, Zhenghao Liu, Peng Li, Maosong Sun, Zhiyuan Liu
Abstract
Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However, most existing language representation models cannot explicitly handle coreference, which is essential to the coherent understanding of the whole discourse. To address this issue, we present CorefBERT, a novel language representation model that can capture the coreferential relations in context. The experimental results show that, compared with existing baseline models, CorefBERT can achieve significant improvements consistently on various downstream NLP tasks that require coreferential reasoning, while maintaining comparable performance to previous models on other common NLP tasks. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/CorefBERT.- Anthology ID:
- 2020.emnlp-main.582
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7170–7186
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.582
- DOI:
- 10.18653/v1/2020.emnlp-main.582
- Cite (ACL):
- Deming Ye, Yankai Lin, Jiaju Du, Zhenghao Liu, Peng Li, Maosong Sun, and Zhiyuan Liu. 2020. Coreferential Reasoning Learning for Language Representation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7170–7186, Online. Association for Computational Linguistics.
- Cite (Informal):
- Coreferential Reasoning Learning for Language Representation (Ye et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2020.emnlp-main.582.pdf
- Code
- thunlp/KernelGAT + additional community code
- Data
- CoLA, DocRED, FEVER, GAP Coreference Dataset, GLUE, HotpotQA, MRPC, MRQA, NewsQA, Quoref, SST, SST-2, SearchQA, TriviaQA, WSC, WikiCREM