Back to Search Start Over

Dialog Context Language Modeling with Recurrent Neural Networks

Authors :
Liu, Bing
Lane, Ian
Publication Year :
2017

Abstract

In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without considering dialog interactions. We design recurrent neural network (RNN) based contextual language models that specially track the interactions between speakers in a dialog. Experiment results on Switchboard Dialog Act Corpus show that the proposed model outperforms conventional single turn based RNN language model by 3.3% on perplexity. The proposed models also demonstrate advantageous performance over other competitive contextual language models.<br />Comment: Accepted for publication at ICASSP 2017

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1701.04056
Document Type :
Working Paper