Papers
arxiv:2012.13838

Inserting Information Bottlenecks for Attribution in Transformers

Published on Dec 27, 2020
Authors:
,
,

Abstract

Information bottlenecks are used to analyze feature importance and information flow in BERT, outperforming competitive methods in degradation tests.

AI-generated summary

Pretrained transformers achieve the state of the art across tasks in natural language processing, motivating researchers to investigate their inner mechanisms. One common direction is to understand what features are important for prediction. In this paper, we apply information bottlenecks to analyze the attribution of each feature for prediction on a black-box model. We use BERT as the example and evaluate our approach both quantitatively and qualitatively. We show the effectiveness of our method in terms of attribution and the ability to provide insight into how information flows through layers. We demonstrate that our technique outperforms two competitive methods in degradation tests on four datasets. Code is available at https://github.com/bazingagin/IBA.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2012.13838 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2012.13838 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2012.13838 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.