Deconvolutional Latent-Variable Model for Text Sequence Matching

Authors

  • Dinghan Shen Duke University
  • Yizhe Zhang Duke University
  • Ricardo Henao Duke University
  • Qinliang Su Duke University
  • Lawrence Carin Duke University

Keywords:

Variational auto-encoder, text sequence matching, deconvolutional networks

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.

Downloads

Published

2018-04-27

How to Cite

Shen, D., Zhang, Y., Henao, R., Su, Q., & Carin, L. (2018). Deconvolutional Latent-Variable Model for Text Sequence Matching. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11991