Dialog Context Language Modeling with Recurrent Neural Networks

01/15/2017

∙

by   Bing Liu, et al.

∙

0

∙

share

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 advantageous performance over other competitive contextual language models.