add files for transfer experiments / enable training on multiple datasets sequentially

allenai / deep_qa

A deep NLP library, based on Keras / tf, focused on question answering (but useful for other NLP too)

Apache License 2.0

404 stars 132 forks source link

add files for transfer experiments / enable training on multiple datasets sequentially #193

Closed nelson-liu closed 7 years ago

nelson-liu commented 7 years ago

This is a bunch of python json configs for the transfer experiments I've been running, and it also has some scala files to create the combined SciQ+WDW dataset.

nelson-liu commented 7 years ago

im going to close this PR and abandon the associated changes in the python code -- a much more elegant solution to this problem is to load a model and fit it some more. there's some scala code in here (from when the repos were joined) that is important, so i'll make a pr to deep_qa_experiments with those

nelson-liu commented 7 years ago

nevermind, @matt-gardner already moved the scala code to the experiments repo so no action needs to be taken here.