Structured Attention for Unsupervised Dialogue Structure Induction

TL;DR

This paper introduces a novel unsupervised method using structured attention within a VRNN to learn meaningful dialogue structures, effectively capturing speaker interactions and semantic templates without supervision.

Contribution

It proposes integrating structured attention into VRNNs with discrete latent states for unsupervised dialogue structure induction, improving interpretability and disentanglement.

Findings

Learns semantic dialogue templates in two-party datasets

Discovers speaker distinctions in multi-party dialogues

Outperforms vanilla VRNN in structure learning

Abstract

Inducing a meaningful structural representation from one or a set of dialogues is a crucial but challenging task in computational linguistics. Advancement made in this area is critical for dialogue system design and discourse analysis. It can also be extended to solve grammatical inference. In this work, we propose to incorporate structured attention layers into a Variational Recurrent Neural Network (VRNN) model with discrete latent states to learn dialogue structure in an unsupervised fashion. Compared to a vanilla VRNN, structured attention enables a model to focus on different parts of the source sentence embeddings while enforcing a structural inductive bias. Experiments show that on two-party dialogue datasets, VRNN with structured attention learns semantic structures that are similar to templates used to generate this dialogue corpus. While on multi-party dialogue datasets, our model learns an interactive structure demonstrating its capability of distinguishing speakers or addresses, automatically disentangling dialogues without explicit human annotation.