Topic compositional neural language model

Published

Conference Paper

Copyright 2018 by the author(s). We propose a Topic Compositional Neural Language Model (TCNLM), a novel method designed to simultaneously capture both the global semantic meaning and the local word-ordering structure in a document. The TCNLM learns the global semantic coherence of a document via a neural topic model, and the probability of each learned latent topic is further used to build a Mixture-of-Experts (MoE) language model, where each expert (corresponding to one topic) is a recurrent neural network (RNN) that accounts for learning the local structure of a word sequence. In order to train the MoE model efficiently, a matrix factorization method is applied, by extending each weight matrix of the RNN to be an ensemble of topic-dependent weight matrices. The degree to which each member of the ensemble is used is tied to the document-dependent probability of the corresponding topics. Experimental results on several corpora show that the proposed approach outperforms both a pure RNN-based model and other topic-guided language models. Further, our model yields sensible topics, and also has the capacity to generate meaningful sentences conditioned on given topics.

Duke Authors

Cited Authors

  • Wang, W; Gan, Z; Shen, D; Huang, J; Ping, W; Satheesh, S; Carin, L

Published Date

  • January 1, 2018

Published In

  • International Conference on Artificial Intelligence and Statistics, Aistats 2018

Start / End Page

  • 356 - 365

Citation Source

  • Scopus