Pareto Probing: Trading Off Accuracy for Complexity

Tiago Pimentel, Naomi Saphra, Adina Williams, Ryan Cotterell


Abstract
The question of how to probe contextual word representations in a way that is principled and useful has seen significant recent attention. In our contribution to this discussion, we argue, first, for a probe metric that reflects the trade-off between probe complexity and performance: the Pareto hypervolume. To measure complexity, we present a number of parametric and non-parametric metrics. Our experiments with such metrics show that probe’s performance curves often fail to align with widely accepted rankings between language representations (with, e.g., non-contextual representations outperforming contextual ones). These results lead us to argue, second, that common simplistic probe tasks such as POS labeling and dependency arc labeling, are inadequate to evaluate the properties encoded in contextual word representations. We propose full dependency parsing as an example probe task, and demonstrate it with the Pareto hypervolume. In support of our arguments, the results of this illustrative experiment conform closer to accepted rankings among contextual word representations.
Anthology ID:
2020.emnlp-main.254
Original:
2020.emnlp-main.254v1
Version 2:
2020.emnlp-main.254v2
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3138–3153
Language:
URL:
https://aclanthology.org/2020.emnlp-main.254
DOI:
10.18653/v1/2020.emnlp-main.254
Bibkey:
Cite (ACL):
Tiago Pimentel, Naomi Saphra, Adina Williams, and Ryan Cotterell. 2020. Pareto Probing: Trading Off Accuracy for Complexity. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3138–3153, Online. Association for Computational Linguistics.
Cite (Informal):
Pareto Probing: Trading Off Accuracy for Complexity (Pimentel et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.254.pdf
Video:
 https://slideslive.com/38938932
Code
 rycolab/pareto-probing