search

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 train logs for asreader_who_did_what experiment #174

Closed nelson-liu closed 7 years ago

matt-gardner commented 7 years ago

Hmm, I would probably put this in a condensed form somehow on a new page under doc/, instead of committing the actual log file. I might put it here: http://deep-qa.readthedocs.io/en/latest/models/about_models.html, though I'm not sure yet.

nelson-liu commented 7 years ago

yeah, i'm not too sure where or how to present it as well --- we can leave this open until we think of a good solution.

matt-gardner commented 7 years ago

I'd probably add a section under About Models listing all of the models we can reproduce, including references to papers, links to the experiment json file / scala code to run the experiment, the result we got, and the running time (including on what machine). My only question is whether to have this in the About Models page, or somewhere else (e.g., one section like this under each type of model).

nelson-liu commented 7 years ago

still unsure where this should go...

nelson-liu commented 7 years ago

i cant think of a centralized place to put these things, so i'm going to close this for now; the files will remain on my branch / these results are documented so I don't think we're losing much.

matt-gardner commented 7 years ago

Maybe you could add a section to this page that lists some of the more popular models that we have implemented (with links to the docs for the actual implementation), and gives results from training those models with our code.