Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction
Open Access
- 15 September 2020
- journal article
- Published by Association for Natural Language Processing in Journal of Natural Language Processing
- Vol. 27 (3) , 683-687
Abstract
No abstract availableThis publication has 16 references indexed in Scilit:
- TMU Transformer System Using BERT for Re-ranking at BEA 2019 Grammatical Error Correction on Restricted Track2019
- The AIP-Tohoku System at the BEA-2019 Shared Task2019
- Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data2019
- Cross-Sentence Grammatical Error Correction2019
- Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data2019
- Corpora Generation for Grammatical Error Correction2019
- Noising and Denoising Natural Language: Diverse Backtranslation for Grammar Correction2018
- JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction2017
- Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction2017
- The CoNLL-2014 Shared Task on Grammatical Error Correction2014