MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective
Xiao Wang, Shihan Dou, Limao Xiong, Yicheng Zou, Qi Zhang, Tao Gui, Liang Qiao, Zhanzhan Cheng, Xuanjing Huang
Abstract
NER model has achieved promising performance on standard NER benchmarks. However, recent studies show that previous approaches may over-rely on entity mention information, resulting in poor performance on out-of-vocabulary(OOV) entity recognition. In this work, we propose MINER, a novel NER learning framework, to remedy this issue from an information-theoretic perspective. The proposed approach contains two mutual information based training objectives: i) generalizing information maximization, which enhances representation via deep understanding of context and entity surface forms; ii) superfluous information minimization, which discourages representation from rotate memorizing entity names or exploiting biased cues in data. Experiments on various settings and datasets demonstrate that it achieves better performance in predicting OOV entities.- Anthology ID:
- 2022.acl-long.383
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5590–5600
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.383
- DOI:
- 10.18653/v1/2022.acl-long.383
- Cite (ACL):
- Xiao Wang, Shihan Dou, Limao Xiong, Yicheng Zou, Qi Zhang, Tao Gui, Liang Qiao, Zhanzhan Cheng, and Xuanjing Huang. 2022. MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5590–5600, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective (Wang et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2022.acl-long.383.pdf
- Code
- beyonderxx/miner + additional community code
- Data
- JNLPBA, WNUT 2017