UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues

Hung Le, Doyen Sahoo, Chenghao Liu, Nancy Chen, Steven C.H. Hoi


Abstract
Building an end-to-end conversational agent for multi-domain task-oriented dialogues has been an open challenge for two main reasons. First, tracking dialogue states of multiple domains is non-trivial as the dialogue agent must obtain complete states from all relevant domains, some of which might have shared slots among domains as well as unique slots specifically for one domain only. Second, the dialogue agent must also process various types of information across domains, including dialogue context, dialogue states, and database, to generate natural responses to users. Unlike the existing approaches that are often designed to train each module separately, we propose “UniConv” - a novel unified neural architecture for end-to-end conversational systems in multi-domain task-oriented dialogues, which is designed to jointly train (i) a Bi-level State Tracker which tracks dialogue states by learning signals at both slot and domain level independently, and (ii) a Joint Dialogue Act and Response Generator which incorporates information from various input components and models dialogue acts and target responses simultaneously. We conduct comprehensive experiments in dialogue state tracking, context-to-text, and end-to-end settings on the MultiWOZ2.1 benchmark, achieving superior performance over competitive baselines.
Anthology ID:
2020.emnlp-main.146
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1860–1877
Language:
URL:
https://aclanthology.org/2020.emnlp-main.146
DOI:
10.18653/v1/2020.emnlp-main.146
Bibkey:
Cite (ACL):
Hung Le, Doyen Sahoo, Chenghao Liu, Nancy Chen, and Steven C.H. Hoi. 2020. UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1860–1877, Online. Association for Computational Linguistics.
Cite (Informal):
UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues (Le et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.146.pdf
Video:
 https://slideslive.com/38938827
Code
 henryhungle/UniConv