Unsupervised Learning of Hierarchical Conversation Structure

TL;DR

This paper presents an unsupervised method for learning hierarchical structures in conversations, identifying dialogue acts and sub-tasks, which improves understanding and interpretability in dialogue systems.

Contribution

It introduces a novel unsupervised approach to discover hierarchical conversation structures, enhancing neural language models and interpretability without domain-specific annotations.

Findings

Improves conversation understanding tasks

Provides interpretable sub-dialogue networks

Enhances neural models with learned structures

Abstract

Human conversations can evolve in many different ways, creating challenges for automatic understanding and summarization. Goal-oriented conversations often have meaningful sub-dialogue structure, but it can be highly domain-dependent. This work introduces an unsupervised approach to learning hierarchical conversation structure, including turn and sub-dialogue segment labels, corresponding roughly to dialogue acts and sub-tasks, respectively. The decoded structure is shown to be useful in enhancing neural models of language for three conversation-level understanding tasks. Further, the learned finite-state sub-dialogue network is made interpretable through automatic summarization.