Discovering Conversational Dependencies between Messages in Dialogs
arXiv:1612.02801
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.
AAAI2017 student abstract camera-ready version
Cited by in corpus (5)
- A Large-Scale Corpus for Conversation Disentanglement
- DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement
- Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformer
- Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure
- Multi-turn Response Selection using Dialogue Dependency Relations