English

LSTM based Conversation Models

Computation and Language 2016-04-01 v1

Abstract

In this paper, we present a conversational model that incorporates both context and participant role for two-party conversations. Different architectures are explored for integrating participant role and context information into a Long Short-term Memory (LSTM) language model. The conversational model can function as a language model or a language generation model. Experiments on the Ubuntu Dialog Corpus show that our model can capture multiple turn interaction between participants. The proposed method outperforms a traditional LSTM model as measured by language model perplexity and response ranking. Generated responses show characteristic differences between the two participant roles.

Keywords

Cite

@article{arxiv.1603.09457,
  title  = {LSTM based Conversation Models},
  author = {Yi Luan and Yangfeng Ji and Mari Ostendorf},
  journal= {arXiv preprint arXiv:1603.09457},
  year   = {2016}
}
R2 v1 2026-06-22T13:22:04.444Z