Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition
This work addresses nested NER, a specific challenge in natural language processing, representing an incremental improvement over existing span-based methods.
The paper tackles the problem of nested named entity recognition by proposing a two-stage identifier that generates span proposals and labels them, addressing issues like high computational cost and poor long entity recognition. It reports outperforming previous state-of-the-art models on nested NER datasets.
Named entity recognition (NER) is a well-studied task in natural language processing. Traditional NER research only deals with flat entities and ignores nested entities. The span-based methods treat entity recognition as a span classification task. Although these methods have the innate ability to handle nested NER, they suffer from high computational cost, ignorance of boundary information, under-utilization of the spans that partially match with entities, and difficulties in long entity recognition. To tackle these issues, we propose a two-stage entity identifier. First we generate span proposals by filtering and boundary regression on the seed spans to locate the entities, and then label the boundary-adjusted span proposals with the corresponding categories. Our method effectively utilizes the boundary information of entities and partially matched spans during training. Through boundary regression, entities of any length can be covered theoretically, which improves the ability to recognize long entities. In addition, many low-quality seed spans are filtered out in the first stage, which reduces the time complexity of inference. Experiments on nested NER datasets demonstrate that our proposed method outperforms previous state-of-the-art models.