An information theoretic view on selecting linguistic probes

Zining Zhu, Frank Rudzicz


Abstract
There is increasing interest in assessing the linguistic knowledge encoded in neural representations. A popular approach is to attach a diagnostic classifier – or ”probe” – to perform supervised classification from internal representations. However, how to select a good probe is in debate. Hewitt and Liang (2019) showed that a high performance on diagnostic classification itself is insufficient, because it can be attributed to either ”the representation being rich in knowledge”, or ”the probe learning the task”, which Pimentel et al. (2020) challenged. We show this dichotomy is valid information-theoretically. In addition, we find that the ”good probe” criteria proposed by the two papers, *selectivity* (Hewitt and Liang, 2019) and *information gain* (Pimentel et al., 2020), are equivalent – the errors of their approaches are identical (modulo irrelevant terms). Empirically, these two selection criteria lead to results that highly agree with each other.
Anthology ID:
2020.emnlp-main.744
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:
9251–9262
Language:
URL:
https://aclanthology.org/2020.emnlp-main.744
DOI:
10.18653/v1/2020.emnlp-main.744
Bibkey:
Cite (ACL):
Zining Zhu and Frank Rudzicz. 2020. An information theoretic view on selecting linguistic probes. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9251–9262, Online. Association for Computational Linguistics.
Cite (Informal):
An information theoretic view on selecting linguistic probes (Zhu & Rudzicz, EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2020.emnlp-main.744.pdf
Video:
 https://slideslive.com/38938744