BiLSTM-JOINT (trained on FCE)

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Grammatical Error CorrectiononJFLEG
F0.5· 2018-11-14
52.52
SOTA
Jointly Learning to Label Sentences and Tokens arXiv:1811.05949
Grammatical Error CorrectiononCoNLL-2014 A1
F0.5· 2018-11-14
22.14
best: 54.3 (VERNet)
Jointly Learning to Label Sentences and Tokens arXiv:1811.05949
Grammatical Error CorrectiononCoNLL-2014 A2
F0.5· 2018-11-14
29.65
best: 63.1 (VERNet)
Jointly Learning to Label Sentences and Tokens arXiv:1811.05949