Structured Attention for Unsupervised Dialogue Structure Induction

Liang Qiu, Yizhou Zhao, Weiyan Shi, Yuan Liang, Feng Shi, Tao Yuan, Zhou Yu, Song-Chun Zhu


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.
Anthology ID:
2020.emnlp-main.148
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1889–1899
Language:
URL:
https://aclanthology.org/2020.emnlp-main.148
DOI:
10.18653/v1/2020.emnlp-main.148
Bibkey:
Cite (ACL):
Liang Qiu, Yizhou Zhao, Weiyan Shi, Yuan Liang, Feng Shi, Tao Yuan, Zhou Yu, and Song-Chun Zhu. 2020. Structured Attention for Unsupervised Dialogue Structure Induction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1889–1899, Online. Association for Computational Linguistics.
Cite (Informal):
Structured Attention for Unsupervised Dialogue Structure Induction (Qiu et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.148.pdf
Optional supplementary material:
 2020.emnlp-main.148.OptionalSupplementaryMaterial.zip
Video:
 https://slideslive.com/38938654
Code
 Liang-Qiu/SVRNN-dialogues