News for hackers. Stuff that matters.

A comment on AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models.

Re:AllenNLP Interpret: A Framework for Explaining Prediction... by ivan_ah on Saturday September 28, 2019 @10:02PM (#21104512)
Wow this is amazing. Check out their interactive demo that lets you see visualizations for various tasks: https://demo.allennlp.org/coreference-resolution/MTA3MDQ4Nw=...

Interpretability is super important... first for technical debugging, and even more important for giving domain experts a view of the model inner working (otherwise they have to just trust the ML model blindly).

[ Parent | on HN ]
Re:AllenNLP Interpret: A Framework for Explaining Prediction... by carljoseph on Sunday September 29, 2019 @08:32AM (#21106655)
Very interesting demo. Thanks for sharing. Unfortunately it doesn't seem to parse Winograd schemas[0] correctly

[0] https://en.wikipedia.org/wiki/Winograd_Schema_Challenge

[ Parent | on HN ]
Re:AllenNLP Interpret: A Framework for Explaining Prediction... by lifeisstillgood on Sunday September 29, 2019 @11:56AM (#21107734)
>>> The city councilmen refused the demonstrators a permit because they [feared/advocated] violence.

I fear that quite a lot of humans won't get that either - am i being overly pessimistic?

[ Parent | on HN ]