arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.04056cs.CL
收藏

基于循环神经网络的对话上下文语言建模

Dialog Context Language Modeling with Recurrent Neural Networks

Carnegie Mellon University(卡内基梅隆大学)

Bing Liu, Ian Lane

摘要:

在这项工作中,我们提出了上下文语言模型,将对话层次的话语信息到语言建模。以往的语境语言模型都是将前面的话语看作一个输入序列,而没有考虑对话的交互作用。我们设计了基于递归神经网络(RNN)的上下文语言模型,专门跟踪对话中说话者之间的交互。在Switchboard Dialog Act语料库上的实验结果表明,该模型在复杂度方面比传统的单轮RNN语言模型提高了3.3%。所提出的模型也表现出优于其他竞争的上下文语言模型的性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑