Stronger Baselines for Grammatical Error Correction Using Pretrained Encoder-Decoder Model
This work addresses efficiency for GEC researchers by eliminating time-consuming pretraining, though it is incremental as it applies existing models to a known task.
The study tackled the problem of time-consuming pretraining in grammatical error correction (GEC) by using pretrained BART models, achieving high performance with results comparable to current strong results in English GEC.
Studies on grammatical error correction (GEC) have reported the effectiveness of pretraining a Seq2Seq model with a large amount of pseudodata. However, this approach requires time-consuming pretraining for GEC because of the size of the pseudodata. In this study, we explore the utility of bidirectional and auto-regressive transformers (BART) as a generic pretrained encoder-decoder model for GEC. With the use of this generic pretrained model for GEC, the time-consuming pretraining can be eliminated. We find that monolingual and multilingual BART models achieve high performance in GEC, with one of the results being comparable to the current strong results in English GEC. Our implementations are publicly available at GitHub (https://github.com/Katsumata420/generic-pretrained-GEC).