Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition

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.

PDF Abstract ACL 2021 PDF ACL 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Nested Named Entity Recognition ACE 2004 Locate and Label F1 87.41 # 7
Named Entity Recognition ACE 2005 Locate and Label F1 86.67 # 4
Nested Named Entity Recognition ACE 2005 Locate and Label F1 86.67 # 9
Named Entity Recognition CoNLL 2003 (English) Locate and Label F1 92.94 # 29
Nested Named Entity Recognition GENIA Locate and Label F1 80.54 # 5
Chinese Named Entity Recognition Weibo NER Locate and Label F1 69.16 # 6

Methods


No methods listed for this paper. Add relevant methods here