Type Enhanced BERT for Correcting NER Errors

Kuai Li, Chen Chen, Tao Yang, Tianming Du, Peijie Yu, Dong Du, Feng Zhang


Abstract
We introduce the task of correcting named entity recognition (NER) errors without re-training model. After an NER model is trained and deployed in production,it makes prediction errors, which usually need to be fixed quickly. To address this problem, we firstly construct a gazetteer containing named entities and corresponding possible entity types. And then, we propose type enhanced BERT (TyBERT),a method that integrates the named entity’s type information into BERT by an adapter layer. When errors are identified, we can repair the model by updating the gazetteer. In other words, the gazetteer becomes a trigger to control NER model’s output. The experiment results in multiple corpus show the effectiveness of our method, which outperforms strong baselines.x
Anthology ID:
2023.findings-acl.445
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7124–7131
Language:
URL:
https://aclanthology.org/2023.findings-acl.445
DOI:
10.18653/v1/2023.findings-acl.445
Bibkey:
Cite (ACL):
Kuai Li, Chen Chen, Tao Yang, Tianming Du, Peijie Yu, Dong Du, and Feng Zhang. 2023. Type Enhanced BERT for Correcting NER Errors. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7124–7131, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Type Enhanced BERT for Correcting NER Errors (Li et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2023.findings-acl.445.pdf