Discovering Conversational Dependencies between Messages in Dialogs

Authors

  • Wenchao Du University of Waterloo
  • Pascal Poupart University of Waterloo
  • Wei Xu The Ohio State University

DOI:

https://doi.org/10.1609/aaai.v31i1.11111

Keywords:

NLP, Discourse, Dialog

Abstract

We investigate the task of inferring conversational dependencies between messages in one-on-one online chat, which has become one of the most popular forms of customer service. We propose a novel probabilistic classifier that leverages conversational, lexical and semantic information. The approach is evaluated empirically on a set of customer service chat logs from a Chinese e-commerce website. It outperforms heuristic baselines.
AAAI-2017 Proceedings Cover

Downloads

Published

2017-02-12

How to Cite

Du, W., Poupart, P., & Xu, W. (2017). Discovering Conversational Dependencies between Messages in Dialogs. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). https://doi.org/10.1609/aaai.v31i1.11111

Issue

Vol. 31 No. 1 (2017): Thirty-First AAAI Conference on Artificial Intelligence

Section

Student Abstract Track