Hero-Gang Neural Model For Named Entity Recognition

TL;DR

This paper introduces the Hero-Gang Neural model for NER, combining Transformer-based global context with local feature extraction to improve entity recognition accuracy.

Contribution

It proposes a novel Hero-Gang neural structure that integrates global and local information for enhanced NER performance.

Findings

Outperforms existing models on benchmark datasets

Effectively combines global and local features

Improves recognition of local position information

Abstract

Named entity recognition (NER) is a fundamental and important task in NLP, aiming at identifying named entities (NEs) from free text. Recently, since the multi-head attention mechanism applied in the Transformer model can effectively capture longer contextual information, Transformer-based models have become the mainstream methods and have achieved significant performance in this task. Unfortunately, although these models can capture effective global context information, they are still limited in the local feature and position information extraction, which is critical in NER. In this paper, to address this limitation, we propose a novel Hero-Gang Neural structure (HGN), including the Hero and Gang module, to leverage both global and local information to promote NER. Specifically, the Hero module is composed of a Transformer-based encoder to maintain the advantage of the self-attention mechanism, and the Gang module utilizes a multi-window recurrent module to extract local features and position information under the guidance of the Hero module. Afterward, the proposed multi-window attention effectively combines global information and multiple local features for predicting entity labels. Experimental results on several benchmark datasets demonstrate the effectiveness of our proposed model.