Measuring Association Between Labels and Free-Text Rationales

Sarah Wiegreffe, Ana Marasović, Noah A. Smith


Abstract
In interpretable NLP, we require faithful rationales that reflect the model’s decision-making process for an explained instance. While prior work focuses on extractive rationales (a subset of the input words), we investigate their less-studied counterpart: free-text natural language rationales. We demonstrate that *pipelines*, models for faithful rationalization on information-extraction style tasks, do not work as well on “reasoning” tasks requiring free-text rationales. We turn to models that *jointly* predict and rationalize, a class of widely used high-performance models for free-text rationalization. We investigate the extent to which the labels and rationales predicted by these models are associated, a necessary property of faithful explanation. Via two tests, *robustness equivalence* and *feature importance agreement*, we find that state-of-the-art T5-based joint models exhibit desirable properties for explaining commonsense question-answering and natural language inference, indicating their potential for producing faithful free-text rationales.
Anthology ID:
2021.emnlp-main.804
Original:
2021.emnlp-main.804v1
Version 2:
2021.emnlp-main.804v2
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10266–10284
Language:
URL:
https://aclanthology.org/2021.emnlp-main.804
DOI:
10.18653/v1/2021.emnlp-main.804
Bibkey:
Cite (ACL):
Sarah Wiegreffe, Ana Marasović, and Noah A. Smith. 2021. Measuring Association Between Labels and Free-Text Rationales. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10266–10284, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Measuring Association Between Labels and Free-Text Rationales (Wiegreffe et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.804.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.804.mp4
Code
 allenai/label_rationale_association
Data
CoS-ECommonsenseQASNLIe-SNLI