Deconvolutional latent-variable model for text sequence matching

Dinghan Shen, Yizhe Zhang, Ricardo Henao, Qinliang Su, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

38 Scopus citations

Abstract

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we employ deconvolutional networks as the sequence decoder (generator), providing learned latent codes with more semantic information and better generalization. Our model, trained in an unsupervised manner, yields stronger empirical predictive performance than a decoder based on Long Short-Term Memory (LSTM), with less parameters and considerably faster training. Further, we apply it to text sequence-matching problems. The proposed model significantly outperforms several strong sentence-encoding baselines, especially in the semi-supervised setting.
Original languageEnglish (US)
Title of host publication32nd AAAI Conference on Artificial Intelligence, AAAI 2018
PublisherAAAI press
Pages5438-5445
Number of pages8
ISBN (Print)9781577358008
StatePublished - Jan 1 2018
Externally publishedYes

Fingerprint

Dive into the research topics of 'Deconvolutional latent-variable model for text sequence matching'. Together they form a unique fingerprint.

Cite this