TY - GEN
T1 - Exploring semantic properties of sentence embeddings
AU - Zhu, Xunjie
AU - Li, Tingfeng
AU - De Melo, Gerard
N1 - Publisher Copyright:
© 2018 Association for Computational Linguistics
PY - 2018
Y1 - 2018
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85063132274&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063132274&partnerID=8YFLogxK
U2 - 10.18653/v1/p18-2100
DO - 10.18653/v1/p18-2100
M3 - Conference contribution
AN - SCOPUS:85063132274
T3 - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
SP - 632
EP - 637
BT - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
PB - Association for Computational Linguistics (ACL)
T2 - 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Y2 - 15 July 2018 through 20 July 2018
ER -