Hero-Gang Neural Model For Named Entity Recognition

Jinpeng Hu, Yaling Shen, Yang Liu, Xiang Wan, Tsung-Hui Chang


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.
Anthology ID:
2022.naacl-main.140
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1924–1936
Language:
URL:
https://aclanthology.org/2022.naacl-main.140
DOI:
10.18653/v1/2022.naacl-main.140
Bibkey:
Cite (ACL):
Jinpeng Hu, Yaling Shen, Yang Liu, Xiang Wan, and Tsung-Hui Chang. 2022. Hero-Gang Neural Model For Named Entity Recognition. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1924–1936, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Hero-Gang Neural Model For Named Entity Recognition (Hu et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.140.pdf
Software:
 2022.naacl-main.140.software.zip
Code
 jinpeng01/hgn
Data
BC2GMBC5CDROntoNotes 5.0WNUT 2016 NERWNUT 2017