Main should load dataset straight from a file

clay-lab / transductions

A PyTorch framework for creating, running, and reproducing experiments on seq2seq models.

6 stars 3 forks source link

Main should load dataset straight from a file #11

Closed NoahAmsel closed 4 years ago

NoahAmsel commented 4 years ago

Consistent interface that the files are .tsv with three columns: input sequence (which could be in tree format but doesn't have to be) transformation tag output sequence (which could be in tree format but doesn't have to be)