Neural Sequence-Labelling Models for Grammatical Error Correction

Helen Yannakoudakis, Marek Rei, Øistein E. Andersen, Zheng Yuan


Abstract
We propose an approach to N-best list reranking using neural sequence-labelling models. We train a compositional model for error detection that calculates the probability of each token in a sentence being correct or incorrect, utilising the full sentence as context. Using the error detection model, we then re-rank the N best hypotheses generated by statistical machine translation systems. Our approach achieves state-of-the-art results on error correction for three different datasets, and it has the additional advantage of only using a small set of easily computed features that require no linguistic input.
Anthology ID:
D17-1297
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2795–2806
Language:
URL:
https://www.aclweb.org/anthology/D17-1297
DOI:
10.18653/v1/D17-1297
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D17-1297.pdf