ML Research Wiki / Benchmarks / Grammatical Error Correction / JFLEG

JFLEG

Grammatical Error Correction Benchmark

Performance Over Time

📊 Showing 6 results | 📏 Metric: GLEU

Top Performing Models

Rank Model Paper GLEU Date Code
1 VERNet Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction 62.10 2021-05-10 📦 thunlp/VERNet
2 Transformer + Pre-train with Pseudo Data + BERT Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction 62.00 2020-05-03 📦 kanekomasahiro/bert-gec
3 SMT + BiGRU Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation 61.50 2018-04-16 -
4 Copy-augmented Model (4 Ensemble +Denoising Autoencoder) Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data 61.00 2019-03-01 📦 zhawe01/fairseq-gec 📦 yuantiku/fairseq-gec 📦 youichiro/transformer-copy
5 Transformer Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task 59.90 2018-04-16 📦 grammatical/neural-naacl2018
6 CNN Seq2Seq A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction 57.47 2018-01-26 📦 nusnlp/mlconvgec2018 📦 seaweiqing/neuraltalk_plus_charcnn 📦 seaweiqing/image2story

All Papers (6)

thunlp/VERNet
kanekomasahiro/bert-gec
zhawe01/fairseq-gec yuantiku/fairseq-gec
grammatical/neural-naacl2018
nusnlp/mlconvgec2018 seaweiqing/neuraltalk_plus_charcnn seaweiqing/image2story