Improving Syntactic Probing Correctness and Robustness with Control Tasks

Weicheng Ma, Brian Wang, Hefan Zhang, Lili Wang, Rolando Coto-Solano, Saeed Hassanpour, Soroush Vosoughi


Abstract
Syntactic probing methods have been used to examine whether and how pre-trained language models (PLMs) encode syntactic features. However, the probing methods are usually biased by the PLMs’ memorization of common word co-occurrences, even if they do not form syntactic relations. This paper presents a random-word-substitution and random-label-matching control task to reduce these biases and improve the robustness of syntactic probing methods. Our control tasks are also shown to notably improve the consistency of probing results between different probing methods and make the methods more robust with respect to the text attributes of the probing instances. Our control tasks make syntactic probing methods better at reconstructing syntactic features and more generalizable to unseen text domains. Our experiments show that our proposed control tasks are effective on different PLMs, probing methods, and syntactic features.
Anthology ID:
2023.acl-short.35
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
402–415
Language:
URL:
https://aclanthology.org/2023.acl-short.35
DOI:
10.18653/v1/2023.acl-short.35
Bibkey:
Cite (ACL):
Weicheng Ma, Brian Wang, Hefan Zhang, Lili Wang, Rolando Coto-Solano, Saeed Hassanpour, and Soroush Vosoughi. 2023. Improving Syntactic Probing Correctness and Robustness with Control Tasks. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 402–415, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Improving Syntactic Probing Correctness and Robustness with Control Tasks (Ma et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-short.35.pdf
Video:
 https://aclanthology.org/2023.acl-short.35.mp4