Neural rationale models are popular for interpretable predictions of NLP tasks . In these, a selector extracts segments of the input text, calledrationales, and passes these segments to a classifier for prediction . We call for more rigorous evaluations of these models to ensure desired properties ofinterpretability are achieved . The code can be found athttps://://://github.com/yimingz89/Neural-Rationale-Analysis. The code is available to download and use in the wild .

Author(s) : Yiming Zheng, Serena Booth, Julie Shah, Yilun Zhou

Links : PDF - Abstract

Code :
Coursera

Keywords : neural - rationale - models - code - segments -

Leave a Reply

Your email address will not be published. Required fields are marked *