MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective
This addresses a key limitation in NER models for applications requiring robust handling of unseen entities, though it appears incremental as it builds on existing NER approaches.
The paper tackles the problem of poor performance in out-of-vocabulary (OOV) named entity recognition by proposing MINER, a framework that uses information-theoretic objectives to reduce over-reliance on entity mention information, resulting in improved OOV entity prediction across various datasets and settings.
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.