DeepAI AI Chat
Log In Sign Up

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

by   Hung Le, et al.
Singapore Management University
Agency for Science, Technology and Research

Building an end-to-end conversational agent for multi-domain task-oriented dialogue 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 in all tasks. Our code and models will be released.


Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System

Task-Oriented Dialogue (TOD) systems are designed to carry out specific ...

Exploring the importance of context and embeddings in neural NER models for task-oriented dialogue systems

Named Entity Recognition (NER), a classic sequence labelling task, is an...

AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue

The problem of building a coherent and non-monotonous conversational age...

Towards Task-Oriented Dialogue in Mixed Domains

This work investigates the task-oriented dialogue problem in mixed-domai...

Hierarchical Context Enhanced Multi-Domain Dialogue System for Multi-domain Task Completion

Task 1 of the DSTC8-track1 challenge aims to develop an end-to-end multi...

Generating Challenge Datasets for Task-Oriented Conversational Agents through Self-Play

End-to-end neural approaches are becoming increasingly common in convers...