Published on Thu Sep 05 2019

Towards Task-Oriented Dialogue in Mixed Domains

Tho Luong Chi, Phuong Le-Hong

This work investigates the task-oriented dialogue problem in mixed-domain settings. We first show that a specialized state tracking component in multiple domains plays an important role. We then propose a hybrid system which is able to improve the belief tracking accuracy of about 28%.

0
0
0
Abstract

This work investigates the task-oriented dialogue problem in mixed-domain settings. We study the effect of alternating between different domains in sequences of dialogue turns using two related state-of-the-art dialogue systems. We first show that a specialized state tracking component in multiple domains plays an important role and gives better results than an end-to-end task-oriented dialogue system. We then propose a hybrid system which is able to improve the belief tracking accuracy of about 28% of average absolute point on a standard multi-domain dialogue dataset. These experimental results give some useful insights for improving our commercial chatbot platform FPT.AI, which is currently deployed for many practical chatbot applications.

Tue Jul 17 2018
NLP
Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing
The tasks that dialogue systems are trying to solve are becoming increasingly complex. Most current approaches have difficulty scaling up with domains. A novel approach is introduced that fully utilizes semantic similarity between dialogue utterances and the ontology terms.
0
0
0
Wed May 27 2020
Artificial Intelligence
Rethinking Dialogue State Tracking with Reasoning
Policy learning is a bottleneck in dialogue management. This paper proposes to track dialogue states gradually with reasoning over dialogue turns. It significantly outperforms the state-of-the-art methods by 38.6% in terms of joint belief accuracy.
0
0
0
Wed Apr 29 2020
Machine Learning
UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues
"UniConv" is a novel unified neural architecture for end-to-end conversational systems. It is designed to jointly train a State Tracker and Response Generator. It incorporates information from various input components and models dialogue acts and target responses.
0
0
0
Thu Sep 09 2021
NLP
Fusing task-oriented and open-domain dialogues in conversational agents
The goal of building intelligent dialogue systems has largely been pursued under two paradigms: task-oriented dialogue (TOD) systems and open-domain dialogue (ODD) systems. The two dialogue modes can potentially be intertwined together seamlessly in the same conversation. Such ability is desirable in conversational agents, as the integration makes them more accessible and useful.
0
0
0
Sat Sep 29 2018
NLP
MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
The Multi-Domain Wizard-of-Oz dataset (MultiWOZ) is a fully-labeled collection of human-human written conversations. At a size of k dialogues, it is at least one order of magnitude larger than all previous task-oriented
0
0
0
Sun Jan 17 2021
NLP
Few Shot Dialogue State Tracking using Meta-learning
Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals. With the increasing need to deploy such systems in new domains, solving the problem of zero/few-shot DST has become necessary.
0
0
0