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
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.
BibTeX
@inproceedings{wang-etal-2022-miner,
title = "{MINER}: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective",
author = "Wang, Xiao and
Dou, Shihan and
Xiong, Limao and
Zou, Yicheng and
Zhang, Qi and
Gui, Tao and
Qiao, Liang and
Cheng, Zhanzhan and
Huang, Xuanjing",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.383/",
doi = "10.18653/v1/2022.acl-long.383",
pages = "5590--5600"
}