CNN Seq2Seq

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Natural Language Processing4 results

Grammatical Error CorrectiononCoNLL-2014 Shared Task
F0.5· 2018-01-26
54.79
best: 72.8 (Ensembles of best 7 models + GRECO + GTP-rerank)
SOTA
A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction arXiv:1801.08831
Grammatical Error CorrectiononJFLEG
GLEU· 2018-01-26
57.47
best: 62.1 (VERNet)
SOTA
A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction arXiv:1801.08831
Grammatical Error CorrectiononCoNLL-2014 Shared Task (10 annotations)
F0.5· 2018-01-26
70.14
best: 85.21 (GRECO (vote+ESC))
SOTA
A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction arXiv:1801.08831
Grammatical Error Correctionon_Restricted_
GLEU· 2018-01-26
57.47
best: 59.9 (Transformer)
SOTA
A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction arXiv:1801.08831