MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective

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 rote 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.

PDF Abstract ACL 2022 PDF ACL 2022 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Named Entity Recognition (NER) JNLPBA MINER F1 77.03 # 15
Named Entity Recognition (NER) WNUT 2017 MINER F1 54.86 # 9

Methods


No methods listed for this paper. Add relevant methods here