Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction
Abstract
This paper investigates how to effectively incorporate a pre-trained masked language model (MLM), such as BERT, into an encoder-decoder (EncDec) model for grammatical error correction (GEC). The answer to this question is not as straightforward as one might expect because the previous common methods for incorporating a MLM into an EncDec model have potential drawbacks when applied to GEC. For example, the distribution of the inputs to a GEC model can be considerably different (erroneous, clumsy, etc.) from that of the corpora used for pre-training MLMs; however, this issue is not addressed in the previous methods. Our experiments show that our proposed method, where we first fine-tune a MLM with a given GEC corpus and then use the output of the fine-tuned MLM as additional features in the GEC model, maximizes the benefit of the MLM. The best-performing model achieves state-of-the-art performances on the BEA-2019 and CoNLL-2014 benchmarks. Our code is publicly available at: https://github.com/kanekomasahiro/bert-gec.
Cite
@article{arxiv.2005.00987,
title = {Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction},
author = {Masahiro Kaneko and Masato Mita and Shun Kiyono and Jun Suzuki and Kentaro Inui},
journal= {arXiv preprint arXiv:2005.00987},
year = {2020}
}
Comments
Accepted as a short paper to the 58th Annual Conference of the Association for Computational Linguistics (ACL-2020)