Sentence-Level Grammatical Error Identification as Sequence-to-Sequence Correction
Abstract
We demonstrate that an attention-based encoder-decoder model can be used for sentence-level grammatical error identification for the Automated Evaluation of Scientific Writing (AESW) Shared Task 2016. The attention-based encoder-decoder models can be used for the generation of corrections, in addition to error identification, which is of interest for certain end-user applications. We show that a character-based encoder-decoder model is particularly effective, outperforming other results on the AESW Shared Task on its own, and showing gains over a word-based counterpart. Our final model--a combination of three character-based encoder-decoder models, one word-based encoder-decoder model, and a sentence-level CNN--is the highest performing system on the AESW 2016 binary prediction Shared Task.
Cite
@article{arxiv.1604.04677,
title = {Sentence-Level Grammatical Error Identification as Sequence-to-Sequence Correction},
author = {Allen Schmaltz and Yoon Kim and Alexander M. Rush and Stuart M. Shieber},
journal= {arXiv preprint arXiv:1604.04677},
year = {2016}
}
Comments
To appear at BEA11, as part of the AESW 2016 Shared Task