Information-Theoretic Probing for Linguistic Structure

Tiago Pimentel, Josef Valvoda, Rowan Hall Maudslay, Ran Zmigrod, Adina Williams, Ryan Cotterell


Abstract
The success of neural networks on a diverse set of NLP tasks has led researchers to question how much these networks actually “know” about natural language. Probes are a natural way of assessing this. When probing, a researcher chooses a linguistic task and trains a supervised model to predict annotations in that linguistic task from the network’s learned representations. If the probe does well, the researcher may conclude that the representations encode knowledge related to the task. A commonly held belief is that using simpler models as probes is better; the logic is that simpler models will identify linguistic structure, but not learn the task itself. We propose an information-theoretic operationalization of probing as estimating mutual information that contradicts this received wisdom: one should always select the highest performing probe one can, even if it is more complex, since it will result in a tighter estimate, and thus reveal more of the linguistic information inherent in the representation. The experimental portion of our paper focuses on empirically estimating the mutual information between a linguistic property and BERT, comparing these estimates to several baselines. We evaluate on a set of ten typologically diverse languages often underrepresented in NLP research—plus English—totalling eleven languages. Our implementation is available in https://github.com/rycolab/info-theoretic-probing.
Anthology ID:
2020.acl-main.420
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4609–4622
Language:
URL:
https://aclanthology.org/2020.acl-main.420
DOI:
10.18653/v1/2020.acl-main.420
Bibkey:
Cite (ACL):
Tiago Pimentel, Josef Valvoda, Rowan Hall Maudslay, Ran Zmigrod, Adina Williams, and Ryan Cotterell. 2020. Information-Theoretic Probing for Linguistic Structure. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4609–4622, Online. Association for Computational Linguistics.
Cite (Informal):
Information-Theoretic Probing for Linguistic Structure (Pimentel et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2020.acl-main.420.pdf
Video:
 http://slideslive.com/38928922
Code
 rycolab/info-theoretic-probing