DeepAI AI Chat
Log In Sign Up

Incremental Learning from Scratch for Task-Oriented Dialogue Systems

by   Weikang Wang, et al.
Mobvoi, Inc.

Clarifying user needs is essential for existing task-oriented dialogue systems. However, in real-world applications, developers can never guarantee that all possible user demands are taken into account in the design phase. Consequently, existing systems will break down when encountering unconsidered user needs. To address this problem, we propose a novel incremental learning framework to design task-oriented dialogue systems, or for short Incremental Dialogue System (IDS), without pre-defining the exhaustive list of user needs. Specifically, we introduce an uncertainty estimation module to evaluate the confidence of giving correct responses. If there is high confidence, IDS will provide responses to users. Otherwise, humans will be involved in the dialogue process, and IDS can learn from human intervention through an online learning module. To evaluate our method, we propose a new dataset which simulates unanticipated user needs in the deployment stage. Experiments show that IDS is robust to unconsidered user actions, and can update itself online by smartly selecting only the most effective training data, and hence attains better performance with less annotation cost.


page 1

page 2

page 3

page 4


Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?

Task-oriented dialogue (TOD) systems have assisted users on many tasks, ...

Integrating User and Agent Models: A Deep Task-Oriented Dialogue System

Task-oriented dialogue systems can efficiently serve a large number of c...

A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Example

Though widely used in industry, traditional task-oriented dialogue syste...

High-Quality Diversification for Task-Oriented Dialogue Systems

Many task-oriented dialogue systems use deep reinforcement learning (DRL...

Towards End-to-End Learning for Efficient Dialogue Agent by Modeling Looking-ahead Ability

Learning an efficient manager of dialogue agent from data with little ma...