Is Attention Interpretable?

Sofia Serrano, Noah A. Smith


Abstract
Attention mechanisms have recently boosted performance on a range of NLP tasks. Because attention layers explicitly weight input components’ representations, it is also often assumed that attention can be used to identify information that models found important (e.g., specific contextualized word tokens). We test whether that assumption holds by manipulating attention weights in already-trained text classification models and analyzing the resulting differences in their predictions. While we observe some ways in which higher attention weights correlate with greater impact on model predictions, we also find many ways in which this does not hold, i.e., where gradient-based rankings of attention weights better predict their effects than their magnitudes. We conclude that while attention noisily predicts input components’ overall importance to a model, it is by no means a fail-safe indicator.
Anthology ID:
P19-1282
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2931–2951
Language:
URL:
https://aclanthology.org/P19-1282
DOI:
10.18653/v1/P19-1282
Bibkey:
Cite (ACL):
Sofia Serrano and Noah A. Smith. 2019. Is Attention Interpretable?. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2931–2951, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Is Attention Interpretable? (Serrano & Smith, ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1282.pdf
Video:
 https://aclanthology.org/P19-1282.mp4
Code
 serrano-s/attn-tests
Data
Yahoo! Answers