A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching

Jihun Choi, Taeuk Kim, Sang-goo Lee


Abstract
We present a latent variable model for predicting the relationship between a pair of text sequences. Unlike previous auto-encoding–based approaches that consider each sequence separately, our proposed framework utilizes both sequences within a single model by generating a sequence that has a given relationship with a source sequence. We further extend the cross-sentence generating framework to facilitate semi-supervised training. We also define novel semantic constraints that lead the decoder network to generate semantically plausible and diverse sequences. We demonstrate the effectiveness of the proposed model from quantitative and qualitative experiments, while achieving state-of-the-art results on semi-supervised natural language inference and paraphrase identification.
Anthology ID:
P19-1469
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:
4747–4761
URL:
https://www.aclweb.org/anthology/P19-1469
DOI:
10.18653/v1/P19-1469
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/P19-1469.pdf