Cross-Sentence Grammatical Error Correction

Shamil Chollampatt, Weiqi Wang, Hwee Tou Ng


Abstract
Automatic grammatical error correction (GEC) research has made remarkable progress in the past decade. However, all existing approaches to GEC correct errors by considering a single sentence alone and ignoring crucial cross-sentence context. Some errors can only be corrected reliably using cross-sentence context and models can also benefit from the additional contextual information in correcting other errors. In this paper, we address this serious limitation of existing approaches and improve strong neural encoder-decoder models by appropriately modeling wider contexts. We employ an auxiliary encoder that encodes previous sentences and incorporate the encoding in the decoder via attention and gating mechanisms. Our approach results in statistically significant improvements in overall GEC performance over strong baselines across multiple test sets. Analysis of our cross-sentence GEC model on a synthetic dataset shows high performance in verb tense corrections that require cross-sentence context.
Anthology ID:
P19-1042
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
435–445
Language:
URL:
https://aclanthology.org/P19-1042
DOI:
10.18653/v1/P19-1042
Bibkey:
Cite (ACL):
Shamil Chollampatt, Weiqi Wang, and Hwee Tou Ng. 2019. Cross-Sentence Grammatical Error Correction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 435–445, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Cross-Sentence Grammatical Error Correction (Chollampatt et al., ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/P19-1042.pdf
Code
 nusnlp/crosentgec
Data
FCE