Empirical Linguistic Study of Sentence Embeddings

Katarzyna Krasnowska-Kieraś, Alina Wróblewska


Abstract
The purpose of the research is to answer the question whether linguistic information is retained in vector representations of sentences. We introduce a method of analysing the content of sentence embeddings based on universal probing tasks, along with the classification datasets for two contrasting languages. We perform a series of probing and downstream experiments with different types of sentence embeddings, followed by a thorough analysis of the experimental results. Aside from dependency parser-based embeddings, linguistic information is retained best in the recently proposed LASER sentence embeddings.
Anthology ID:
P19-1573
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5729–5739
Language:
URL:
https://www.aclweb.org/anthology/P19-1573
DOI:
10.18653/v1/P19-1573
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/P19-1573.pdf
Video:
 https://vimeo.com/385428708