MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition

Shuang Wu, Xiaoning Song, Zhenhua Feng


Abstract
Recently, word enhancement has become very popular for Chinese Named Entity Recognition (NER), reducing segmentation errors and increasing the semantic and boundary information of Chinese words. However, these methods tend to ignore the information of the Chinese character structure after integrating the lexical information. Chinese characters have evolved from pictographs since ancient times, and their structure often reflects more information about the characters. This paper presents a novel Multi-metadata Embedding based Cross-Transformer (MECT) to improve the performance of Chinese NER by fusing the structural information of Chinese characters. Specifically, we use multi-metadata embedding in a two-stream Transformer to integrate Chinese character features with the radical-level embedding. With the structural characteristics of Chinese characters, MECT can better capture the semantic information of Chinese characters for NER. The experimental results obtained on several well-known benchmarking datasets demonstrate the merits and superiority of the proposed MECT method.
Anthology ID:
2021.acl-long.121
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1529–1539
Language:
URL:
https://aclanthology.org/2021.acl-long.121
DOI:
10.18653/v1/2021.acl-long.121
Bibkey:
Cite (ACL):
Shuang Wu, Xiaoning Song, and Zhenhua Feng. 2021. MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1529–1539, Online. Association for Computational Linguistics.
Cite (Informal):
MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition (Wu et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.121.pdf
Video:
 https://aclanthology.org/2021.acl-long.121.mp4
Code
 CoderMusou/MECT4CNER