The 53rd Statistical Machine Learning Seminar (2023.1.6)
This is an online seminar. Please register at the following Google Forms. A Zoom link will be emailed to you.
Time:
January 6 (Fri), 2023. 13:30 - 15:00
Place:
Zoom (online)
Speaker:
Damien Garreau (Universite Cote d'Azur)
Title:
A Sea of Words: An In-Depth Analysis of Anchors for Text Data
Abstract:
Anchors [Ribeiro et al. (2018)] is a post-hoc, rule-based interpretability method. For text data, it proposes to explain a decision by highlighting a small set of words (an anchor) such that the model to explain has similar outputs when they are present in a document. In this talk, I will present the first theoretical analysis of Anchors, considering that the search for the best anchor is exhaustive. I will show how one can use this analysis to gain insights on the behavior of Anchors on simple models, including elementary if-then rules and linear classifiers.
Preprint: https://arxiv.org/abs/2205.13789