Open howardyclo opened 5 years ago
The error correction model and the error generation model are dual and both of them are dynamically updated, which improves each other: the disfluency candidates produced by error generation model can benefit training the error correction model, while the disfluency candidates created by error correction model can be used as training data for the error generation model.
The purposed strategies can be easily extended to utilize massive native text data, where we can additionally increase correct-correct sentence pairs from native data.
(Note: See tables in the paper, we only provide analysis here)
Unlike the models trained only with original error-corrected data, we propose a novel fluency boost learning mechanism for dynamic data augmentation along with training for GEC, despite some related studies that explore artificial error generation for GEC.
We propose fluency boost inference which allows the model to repeatedly edit a sentence as long as the sentence’s fluency can be improved. To the best of our knowledge, it is the first to conduct multi-round seq2seq inference for GEC, while similar ideas have been proposed for NMT (Xia et al., 2017).
Metadata