Structured Attention for Unsupervised Dialogue Structure Induction

09/17/2020
by   Liang Qiu, et al.
5

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/15/2021

Structural Modeling for Dialogue Disentanglement

Tangled multi-party dialogue context leads to challenges for dialogue re...
research
10/09/2021

Improving Multi-Party Dialogue Discourse Parsing via Domain Integration

While multi-party conversations are often less structured than monologue...
research
09/09/2021

Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehension

Multi-party multi-turn dialogue comprehension brings unprecedented chall...
research
10/07/2021

Multi-tasking Dialogue Comprehension with Discourse Parsing

Multi-party dialogue machine reading comprehension (MRC) raises an even ...
research
05/25/2017

Learning Structured Text Representations

In this paper, we focus on learning structure-aware document representat...
research
05/31/2019

GSN: A Graph-Structured Network for Multi-Party Dialogues

Existing neural models for dialogue response generation assume that utte...
research
07/25/2022

A Multi-Party Dialogue Ressource in French

We present Dialogues in Games (DinG), a corpus of manual transcriptions ...

Please sign up or login with your details

Forgot password? Click here to reset