Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?

Abhilasha Ravichander, Yonatan Belinkov, Eduard Hovy


Abstract
Although neural models have achieved impressive results on several NLP benchmarks, little is understood about the mechanisms they use to perform language tasks. Thus, much recent attention has been devoted to analyzing the sentence representations learned by neural encoders, through the lens of ‘probing’ tasks. However, to what extent was the information encoded in sentence representations, as discovered through a probe, actually used by the model to perform its task? In this work, we examine this probing paradigm through a case study in Natural Language Inference, showing that models can learn to encode linguistic properties even if they are not needed for the task on which the model was trained. We further identify that pretrained word embeddings play a considerable role in encoding these properties rather than the training task itself, highlighting the importance of careful controls when designing probing experiments. Finally, through a set of controlled synthetic tasks, we demonstrate models can encode these properties considerably above chance-level, even when distributed in the data as random noise, calling into question the interpretation of absolute claims on probing tasks.
Anthology ID:
2021.eacl-main.295
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3363–3377
Language:
URL:
https://aclanthology.org/2021.eacl-main.295
DOI:
10.18653/v1/2021.eacl-main.295
Bibkey:
Cite (ACL):
Abhilasha Ravichander, Yonatan Belinkov, and Eduard Hovy. 2021. Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3363–3377, Online. Association for Computational Linguistics.
Cite (Informal):
Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance? (Ravichander et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.295.pdf
Data
MultiNLI