Probing as Quantifying Inductive Bias

Alexander Immer, Lucas Torroba Hennigen, Vincent Fortuin, Ryan Cotterell


Abstract
Pre-trained contextual representations have led to dramatic performance improvements on a range of downstream tasks. Such performance improvements have motivated researchers to quantify and understand the linguistic information encoded in these representations. In general, researchers quantify the amount of linguistic information through probing, an endeavor which consists of training a supervised model to predict a linguistic property directly from the contextual representations. Unfortunately, this definition of probing has been subject to extensive criticism in the literature, and has been observed to lead to paradoxical and counter-intuitive results. In the theoretical portion of this paper, we take the position that the goal of probing ought to be measuring the amount of inductive bias that the representations encode on a specific task. We further describe a Bayesian framework that operationalizes this goal and allows us to quantify the representations’ inductive bias. In the empirical portion of the paper, we apply our framework to a variety of NLP tasks. Our results suggest that our proposed framework alleviates many previous problems found in probing. Moreover, we are able to offer concrete evidence that—for some tasks—fastText can offer a better inductive bias than BERT.
Anthology ID:
2022.acl-long.129
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1839–1851
Language:
URL:
https://aclanthology.org/2022.acl-long.129
DOI:
10.18653/v1/2022.acl-long.129
Bibkey:
Cite (ACL):
Alexander Immer, Lucas Torroba Hennigen, Vincent Fortuin, and Ryan Cotterell. 2022. Probing as Quantifying Inductive Bias. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1839–1851, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Probing as Quantifying Inductive Bias (Immer et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.129.pdf
Video:
 https://aclanthology.org/2022.acl-long.129.mp4
Code
 rycolab/evidence-probing
Data
BoolQ