search

nusnlp / mlconvgec2018

Code and model files for the paper: "A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction" (AAAI-18).
GNU General Public License v3.0
185 stars 73 forks source link

about "scripts/nbest_reformat.py" #7

Closed cwlinghk closed 6 years ago

cwlinghk commented 6 years ago

Should it be 'O' instead of 'S' in line 17? Thank you very much.

shamilcm commented 6 years ago

We use a fork of an older version of Fairseq (https://github.com/shamilcm/fairseq-py/commit/ceb2f1200c9e5b8bf42a1033e7638d3e8586609a) in which it should be 'S'.