DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling
Baojun Wang, Zhao Zhang, Kun Xu, Guang-Yuan Hao, Yuyang Zhang, Lifeng Shang, Linlin Li, Xiao Chen, Xin Jiang, Qun Liu
Abstract
Incorporating lexical knowledge into deep learning models has been proved to be very effective for sequence labeling tasks. However, previous works commonly have difficulty dealing with large-scale dynamic lexicons which often cause excessive matching noise and problems of frequent updates. In this paper, we propose DyLex, a plug-in lexicon incorporation approach for BERT based sequence labeling tasks. Instead of leveraging embeddings of words in the lexicon as in conventional methods, we adopt word-agnostic tag embeddings to avoid re-training the representation while updating the lexicon. Moreover, we employ an effective supervised lexical knowledge denoising method to smooth out matching noise. Finally, we introduce a col-wise attention based knowledge fusion mechanism to guarantee the pluggability of the proposed framework. Experiments on ten datasets of three tasks show that the proposed framework achieves new SOTA, even with very large scale lexicons.- Anthology ID:
- 2021.emnlp-main.211
- 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:
- 2679–2693
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.211
- DOI:
- 10.18653/v1/2021.emnlp-main.211
- Cite (ACL):
- Baojun Wang, Zhao Zhang, Kun Xu, Guang-Yuan Hao, Yuyang Zhang, Lifeng Shang, Linlin Li, Xiao Chen, Xin Jiang, and Qun Liu. 2021. DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2679–2693, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling (Wang et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2021.emnlp-main.211.pdf
- Code
- huawei-noah/noah-research
- Data
- CoNLL 2003