<  Back to the Polytechnique Montréal portal

Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining

Andreas Madsen, Nicholas Meade, Vaibhav Adlakha and Siva Reddy

Paper (2022)

An external link is available for this item
Department: Department of Computer Engineering and Software Engineering
PolyPublie URL: https://publications.polymtl.ca/53481/
Conference Title: Findings of the Association for Computational Linguistics (EMNLP 2022)
Conference Location: Abu Dhabi, United Arab Emirates
Conference Date(s): 2022-12-07 - 2022-12-11
Publisher: Association for Computational Linguistics (ACL)
DOI: 10.18653/v1/2022.findings-emnlp.125
Official URL: https://doi.org/10.18653/v1/2022.findings-emnlp.12...
Date Deposited: 10 Jul 2023 16:30
Last Modified: 05 Apr 2024 11:58
Cite in APA 7: Madsen, A., Meade, N., Adlakha, V., & Reddy, S. (2022, December). Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining [Paper]. Findings of the Association for Computational Linguistics (EMNLP 2022), Abu Dhabi, United Arab Emirates. https://doi.org/10.18653/v1/2022.findings-emnlp.125

Statistics

Dimensions

Repository Staff Only

View Item View Item