Grammatical Error Correction (GEC) Algorithm

From GM-RKB
(Redirected from approaches to GEC)
Jump to navigation Jump to search

A Grammatical Error Correction (GEC) Algorithm is a text error correction algorithm that can be implemented by a GEC system to solve a GEC task (to correct grammatical errors).



References

2018a

2018b

  • (Ge et al., 2018) ⇒ Tao Ge, Furu Wei, and Ming Zhou. (2018). “Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study.” arXiv preprint arXiv:1807.01270
    • ABSTRACT: 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.