Improving Grammatical Error Correction for Multiword Expressions

Shiva Taslimipoor, Christopher Bryant, Zheng Yuan


Abstract
Grammatical error correction (GEC) is the task of automatically correcting errors in text. It has mainly been developed to assist language learning, but can also be applied to native text. This paper reports on preliminary work in improving GEC for multiword expression (MWE) error correction. We propose two systems which incorporate MWE information in two different ways: one is a multi-encoder decoder system which encodes MWE tags in a second encoder, and the other is a BART pre-trained transformer-based system that encodes MWE representations using special tokens. We show improvements in correcting specific types of verbal MWEs based on a modified version of a standard GEC evaluation approach.
Anthology ID:
2022.mwe-1.4
Volume:
Proceedings of the 18th Workshop on Multiword Expressions @LREC2022
Month:
June
Year:
2022
Address:
Marseille, France
Venue:
MWE
SIG:
SIGLEX
Publisher:
European Language Resources Association
Note:
Pages:
9–15
Language:
URL:
https://aclanthology.org/2022.mwe-1.4
DOI:
Bibkey:
Cite (ACL):
Shiva Taslimipoor, Christopher Bryant, and Zheng Yuan. 2022. Improving Grammatical Error Correction for Multiword Expressions. In Proceedings of the 18th Workshop on Multiword Expressions @LREC2022, pages 9–15, Marseille, France. European Language Resources Association.
Cite (Informal):
Improving Grammatical Error Correction for Multiword Expressions (Taslimipoor et al., MWE 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.mwe-1.4.pdf
Data
FCE