Generating Diverse Corrections with Local Beam Search for Grammatical Error Correction

Kengo Hotate, Masahiro Kaneko, Mamoru Komachi


Abstract
In this study, we propose a beam search method to obtain diverse outputs in a local sequence transduction task where most of the tokens in the source and target sentences overlap, such as in grammatical error correction (GEC). In GEC, it is advisable to rewrite only the local sequences that must be rewritten while leaving the correct sequences unchanged. However, existing methods of acquiring various outputs focus on revising all tokens of a sentence. Therefore, existing methods may either generate ungrammatical sentences because they force the entire sentence to be changed or produce non-diversified sentences by weakening the constraints to avoid generating ungrammatical sentences. Considering these issues, we propose a method that does not rewrite all the tokens in a text, but only rewrites those parts that need to be diversely corrected. Our beam search method adjusts the search token in the beam according to the probability that the prediction is copied from the source sentence. The experimental results show that our proposed method generates more diverse corrections than existing methods without losing accuracy in the GEC task.
Anthology ID:
2020.coling-main.193
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2132–2137
Language:
URL:
https://www.aclweb.org/anthology/2020.coling-main.193
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.coling-main.193.pdf