English

Discovering Conversational Dependencies between Messages in Dialogs

Computation and Language 2016-12-09 v1

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.

Keywords

Cite

@article{arxiv.1612.02801,
  title  = {Discovering Conversational Dependencies between Messages in Dialogs},
  author = {Wenchao Du and Pascal Poupart and Wei Xu},
  journal= {arXiv preprint arXiv:1612.02801},
  year   = {2016}
}

Comments

AAAI2017 student abstract camera-ready version

R2 v1 2026-06-22T17:17:53.911Z