A Tale of a Probe and a Parser

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


Abstract
Measuring what linguistic information is encoded in neural models of language has become popular in NLP. Researchers approach this enterprise by training “probes”—supervised models designed to extract linguistic structure from another model’s output. One such probe is the structural probe (Hewitt and Manning, 2019), designed to quantify the extent to which syntactic information is encoded in contextualised word representations. The structural probe has a novel design, unattested in the parsing literature, the precise benefit of which is not immediately obvious. To explore whether syntactic probes would do better to make use of existing techniques, we compare the structural probe to a more traditional parser with an identical lightweight parameterisation. The parser outperforms structural probe on UUAS in seven of nine analysed languages, often by a substantial amount (e.g. by 11.1 points in English). Under a second less common metric, however, there is the opposite trend—the structural probe outperforms the parser. This begs the question: which metric should we prefer?
Anthology ID:
2020.acl-main.659
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7389–7395
Language:
URL:
https://aclanthology.org/2020.acl-main.659
DOI:
10.18653/v1/2020.acl-main.659
Bibkey:
Cite (ACL):
Rowan Hall Maudslay, Josef Valvoda, Tiago Pimentel, Adina Williams, and Ryan Cotterell. 2020. A Tale of a Probe and a Parser. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7389–7395, Online. Association for Computational Linguistics.
Cite (Informal):
A Tale of a Probe and a Parser (Maudslay et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.659.pdf
Video:
 http://slideslive.com/38929294