What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties

Alexis Conneau, German Kruszewski, Guillaume Lample, Loïc Barrault, Marco Baroni


Abstract
Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing. “Downstream” tasks, often based on sentence classification, are commonly used to evaluate the quality of sentence representations. The complexity of the tasks makes it however difficult to infer what kind of information is present in the representations. We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight distinct ways, uncovering intriguing properties of both encoders and training methods.
Anthology ID:
P18-1198
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2126–2136
Language:
URL:
https://www.aclweb.org/anthology/P18-1198
DOI:
10.18653/v1/P18-1198
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/P18-1198.pdf
Note:
 P18-1198.Notes.pdf
Video:
 https://vimeo.com/285805339
Presentation:
 P18-1198.Presentation.pdf