Web: http://arxiv.org/abs/2205.04559

May 11, 2022, 1:11 a.m. | Michael Neely, Stefan F. Schouten, Maurits Bleeker, Ana Lucic

cs.LG updates on arXiv.org arxiv.org

There has been significant debate in the NLP community about whether or not
attention weights can be used as an explanation - a mechanism for interpreting
how important each input token is for a particular prediction. The validity of
"attention as explanation" has so far been evaluated by computing the rank
correlation between attention-based explanations and existing feature
attribution explanations using LSTM-based models. In our work, we (i) compare
the rank correlation between five more recent feature attribution methods and …

artificial artificial intelligence arxiv evaluation explainable artificial intelligence intelligence language natural natural language natural language processing processing

More from arxiv.org / cs.LG updates on arXiv.org

Data & Insights Strategy & Innovation General Manager

@ Chevron Services Company, a division of Chevron U.S.A Inc. | Houston, TX

Faculty members in Research areas such as Bayesian and Spatial Statistics; Data Privacy and Security; AI/ML; NLP; Image and Video Data Analysis

@ Ahmedabad University | Ahmedabad, India

Director, Applied Mathematics & Computational Research Division

@ Lawrence Berkeley National Lab | Berkeley, Ca

Business Data Analyst

@ MainStreet Family Care | Birmingham, AL

Assistant/Associate Professor of the Practice in Business Analytics

@ Georgetown University McDonough School of Business | Washington DC

Senior Data Science Writer

@ NannyML | Remote