Nested Named Entity Recognition as Holistic Structure Parsing

TL;DR

This paper introduces a holistic structure parsing approach for nested NER, modeling full nested entities as a hierarchical structure and incorporating corpus-level information to improve accuracy and domain adaptation.

Contribution

It proposes a novel holistic structure parsing method for nested NER and integrates corpus-aware features like PMI for enhanced performance and domain adaptation.

Findings

Achieves state-of-the-art results on benchmark datasets.

Corpus-aware features significantly improve domain adaptation.

Holistic modeling outperforms linear structure approaches.

Abstract

As a fundamental natural language processing task and one of core knowledge extraction techniques, named entity recognition (NER) is widely used to extract information from texts for downstream tasks. Nested NER is a branch of NER in which the named entities (NEs) are nested with each other. However, most of the previous studies on nested NER usually apply linear structure to model the nested NEs which are actually accommodated in a hierarchical structure. Thus in order to address this mismatch, this work models the full nested NEs in a sentence as a holistic structure, then we propose a holistic structure parsing algorithm to disclose the entire NEs once for all. Besides, there is no research on applying corpus-level information to NER currently. To make up for the loss of this information, we introduce Point-wise Mutual Information (PMI) and other frequency features from corpus-aware statistics for even better performance by holistic modeling from sentence-level to corpus-level. Experiments show that our model yields promising results on widely-used benchmarks which approach or even achieve state-of-the-art. Further empirical studies show that our proposed corpus-aware features can substantially improve NER domain adaptation, which demonstrates the surprising advantage of our proposed corpus-level holistic structure modeling.