search

rgcottrell / pytorch-human-performance-gec

A PyTorch implementation of "Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study"
Apache License 2.0
50 stars 19 forks source link

Training with transformer models #10

Open NikhilCherian opened 4 years ago

NikhilCherian commented 4 years ago

@rgcottrell @tianfeichen @cqlijingwei

I am actually researching about the different types of models for grammatical correction.

So, i used arch='transformer_iwslt_de_en' from this link, https://github.com/pytorch/fairseq/tree/master/examples/translation#iwslt14-german-to-english-transformer

Here, i changed the model from fconv to transformer. I got really disappointing results for the test set, jfleg.

image

Do you want to share some thoughts? What newer features from fairseq do you think will be the fittest for the extension of your project? Any help would be appreciated. Thanks in advance.