Closed dirkweissenborn closed 6 years ago
I've tried it once but nothing was working: I was getting a random-chance test error, and the very same code is getting ~SOTA - ~87% test accuracy - in another codebase. Let me debug this
when did you try? the code has changed, maybe it will work better now.
Let's see!
The code is now very very different from what I have - I have to find some time for looking into this new implementation of ESIM (and DAM eventually), and think what it means in terms of time and papers
I'm not sure I've the time of working on two very distinct implementations of the same thing :( sorry
It is ok to simply run the current implementations as is, host the trained models and report the results in a specific NLI document. No need to look into the code at the moment. We just need some models and numbers.
ESIM's accuracy seems decent (86.6, 86.0) and slightly lower than my implementation (no char inputs, above 87); DAM's seems sub-par (48.0, 48.4), probably it's just a matter of hyperparams.
I'm uploading the models here: http://jack.neuralnoise.com/jack/natural_language_inference/
Done. Happy Holidays!
We need pre-trained models for MultiNLI and SNLI.
... and create some documentation for this task like for extractive QA