Exploring Semantic Properties of Sentence Embeddings

Xunjie Zhu, Tingfeng Li, Gerard de Melo


Abstract
Neural vector representations are ubiquitous throughout all subfields of NLP. While word vectors have been studied in much detail, thus far only little light has been shed on the properties of sentence embeddings. In this paper, we assess to what extent prominent sentence embedding methods exhibit select semantic properties. We propose a framework that generate triplets of sentences to explore how changes in the syntactic structure or semantics of a given sentence affect the similarities obtained between their sentence embeddings.
Anthology ID:
P18-2100
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
632–637
Language:
URL:
https://aclanthology.org/P18-2100
DOI:
10.18653/v1/P18-2100
Bibkey:
Cite (ACL):
Xunjie Zhu, Tingfeng Li, and Gerard de Melo. 2018. Exploring Semantic Properties of Sentence Embeddings. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 632–637, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Exploring Semantic Properties of Sentence Embeddings (Zhu et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-2100.pdf
Presentation:
 P18-2100.Presentation.pdf
Video:
 https://aclanthology.org/P18-2100.mp4
Data
SICK