Neighboring Words Affect Human Interpretation of Saliency Explanations
Alon Jacovi, Hendrik Schuff, Heike Adel, Ngoc Thang Vu, Yoav Goldberg
Abstract
Word-level saliency explanations (“heat maps over words”) are often used to communicate feature-attribution in text-based models. Recent studies found that superficial factors such as word length can distort human interpretation of the communicated saliency scores. We conduct a user study to investigate how the marking of a word’s *neighboring words* affect the explainee’s perception of the word’s importance in the context of a saliency explanation. We find that neighboring words have significant effects on the word’s importance rating. Concretely, we identify that the influence changes based on neighboring direction (left vs. right) and a-priori linguistic and computational measures of phrases and collocations (vs. unrelated neighboring words).Our results question whether text-based saliency explanations should be continued to be communicated at word level, and inform future research on alternative saliency explanation methods.- Anthology ID:
- 2023.findings-acl.750
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11816–11833
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.750
- DOI:
- 10.18653/v1/2023.findings-acl.750
- Cite (ACL):
- Alon Jacovi, Hendrik Schuff, Heike Adel, Ngoc Thang Vu, and Yoav Goldberg. 2023. Neighboring Words Affect Human Interpretation of Saliency Explanations. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11816–11833, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Neighboring Words Affect Human Interpretation of Saliency Explanations (Jacovi et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.findings-acl.750.pdf