Abstract
Character-level BERT pre-trained in Chinese suffers a limitation of lacking lexicon information, which shows effectiveness for Chinese NER. To integrate the lexicon into pre-trained LMs for Chinese NER, we investigate a semi-supervised entity enhanced BERT pre-training method. In particular, we first extract an entity lexicon from the relevant raw text using a new-word discovery method. We then integrate the entity information into BERT using Char-Entity-Transformer, which augments the self-attention using a combination of character and entity representations. In addition, an entity classification task helps inject the entity information into model parameters in pre-training. The pre-trained models are used for NER fine-tuning. Experiments on a news dataset and two datasets annotated by ourselves for NER in long-text show that our method is highly effective and achieves the best results.- Anthology ID:
- 2020.emnlp-main.518
- 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:
- 6384–6396
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.518
- DOI:
- 10.18653/v1/2020.emnlp-main.518
- Cite (ACL):
- Chen Jia, Yuefeng Shi, Qinrong Yang, and Yue Zhang. 2020. Entity Enhanced BERT Pre-training for Chinese NER. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6384–6396, Online. Association for Computational Linguistics.
- Cite (Informal):
- Entity Enhanced BERT Pre-training for Chinese NER (Jia et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2020.emnlp-main.518.pdf