TemplateGEC: Improving Grammatical Error Correction with Detection Template

Yinghao Li, Xuebo Liu, Shuo Wang, Peiyuan Gong, Derek F. Wong, Yang Gao, Heyan Huang, Min Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Citations (Scopus)

Abstract

Grammatical error correction (GEC) can be divided into sequence-to-edit (Seq2Edit) and sequence-to-sequence (Seq2Seq) frameworks, both of which have their pros and cons. To utilize the strengths and make up for the shortcomings of these frameworks, this paper proposes a novel method, TemplateGEC, which capitalizes on the capabilities of both Seq2Edit and Seq2Seq frameworks in error detection and correction respectively. TemplateGEC utilizes the detection labels from a Seq2Edit model, to construct the template as the input. A Seq2Seq model is employed to enforce consistency between the predictions of different templates by utilizing consistency learning. Experimental results on the Chinese NLPCC18, English BEA19 and CoNLL14 benchmarks show the effectiveness and robustness of TemplateGEC. Further analysis reveals the potential of our method in performing human-in-the-loop GEC. Source code and scripts are available at https://github.com/li-aolong/TemplateGEC.

Original languageEnglish
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages6878-6892
Number of pages15
ISBN (Electronic)9781959429722
Publication statusPublished - 2023
Event61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Canada
Duration: 9 Jul 202314 Jul 2023

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume1
ISSN (Print)0736-587X

Conference

Conference61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
Country/TerritoryCanada
CityToronto
Period9/07/2314/07/23

Fingerprint

Dive into the research topics of 'TemplateGEC: Improving Grammatical Error Correction with Detection Template'. Together they form a unique fingerprint.

Cite this