A Tale of a Probe and a Parser


Loading...

Date

2020-07

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

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?

Publication status

published

Book title

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Journal / series

Volume

Pages / Article No.

7389 - 7395

Publisher

Association for Computational Linguistics

Event

58th Annual Meeting of the Association-for-Computational-Linguistics (ACL 2020) (virtual)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

09682 - Cotterell, Ryan / Cotterell, Ryan check_circle

Notes

Due to the Coronavirus (COVID-19) the conference was conducted virtually.

Funding

Related publications and datasets