Fluency Boost Learning and Inference for Neural Grammatical Error Correction

@inproceedings{Ge2018FluencyBL,
  title={Fluency Boost Learning and Inference for Neural Grammatical Error Correction},
  author={Tao Ge and Furu Wei and Ming Zhou},
  booktitle={ACL},
  year={2018}
}
Most of the neural sequence-to-sequence (seq2seq) models for grammatical error correction (GEC) have two limitations: (1) a seq2seq model may not be well generalized with only limited error-corrected data; (2) a seq2seq model may fail to completely correct a sentence with multiple errors through normal seq2seq inference. We attempt to address these limitations by proposing a fluency boost learning and inference mechanism. Fluency boosting learning generates fluency-boost sentence pairs during… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 23 CITATIONS

Automatic annotation of error types for grammatical error correction

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Controllable Data Synthesis Method for Grammatical Error Correction

Chencheng Wang, Liner Yang, Yun Chen, Xiaoyan Du, Erhong Yang
  • ArXiv
  • 2019
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Corpora Generation for Grammatical Error Correction

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Denoising based Sequence-to-Sequence Pre-training for Text Generation

Liang Wang, Wei Zhao, Ruoyu Jia, Sujian Li, Jingming Liu
  • IJCNLP 2019
  • 2019
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Parallel Iterative Edit Models for Local Sequence Transduction

  • IJCNLP 2019
  • 2019
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewriting

Yi Zhang, Tao Ge, Furu Wei, Ming Zhou, Xu Sun
  • ArXiv
  • 2019
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 68 REFERENCES

Ground Truth for Grammatical Error Correction Metrics

Courtney Napoles, Keisuke Sakaguchi, Matt Post, Joel R. Tetreault
  • IJCNLP 2015
  • 2015
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Book Reviews Automated Grammatical Error Detection for Language Learners

Claudia Leacock, Martin Chodorow, Michael Gamon
  • 2011
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

NAIST at 2013 CoNLL Grammatical Error Correction Shared Task

  • CoNLL Shared Task
  • 2013
VIEW 1 EXCERPT
HIGHLY INFLUENTIAL