Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study

About

Neural sequence-to-sequence (seq2seq) approaches have proven to be successful in grammatical error correction (GEC). Based on the seq2seq framework, we propose a novel fluency boost learning and inference mechanism. Fluency boosting learning generates diverse error-corrected sentence pairs during training, enabling the error correction model to learn how to improve a sentence's fluency from more instances, while fluency boosting inference allows the model to correct a sentence incrementally with multiple inference steps. Combining fluency boost learning and inference with convolutional seq2seq models, our approach achieves the state-of-the-art performance: 75.72 (F_{0.5}) on CoNLL-2014 10 annotation dataset and 62.42 (GLEU) on JFLEG test set respectively, becoming the first GEC system that reaches human-level performance (72.58 for CoNLL and 62.37 for JFLEG) on both of the benchmarks.

Tao Ge, Furu Wei, Ming Zhou• 2018

Related benchmarks

TaskDatasetResultRank
Grammatical Error CorrectionCoNLL 2014 (test)
F0.5 Score61.34
207
Grammatical Error CorrectionJFLEG
GLEU62.42
47
Grammatical Error CorrectionJFLEG (test)
GLEU62.42
45
Grammatical Error CorrectionCoNLL 2014
F0.561.34
39
Grammatical Error CorrectionCoNLL-10
F0.5 Score76.88
16
Grammatical Error CorrectionCoNLL-10 SvH
F0.5 Score75.93
7
Showing 6 of 6 rows

Other info

Code

Follow for update