Learning Domain-Independent Dialogue Policies via Ontology Parameterisation

By Zhuoran Wang, Tsung-Hsien Wen, Pei-hao Su, Yannis Stylianou. 2015

37 citations recorded by the source corpus.

This paper introduces a novel approach to eliminate the domain dependence of dialogue state and action representations, such that dialogue policies trained based on the proposed representation can be transferred across different domains. The experimental results show that the policy optimised in a restaurant search domain using our domain-independent representations can be deployed to a laptop sale domain, achieving a task success rate very close (96.4% relative) to that of the policy optimised on in-domain dialogues.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Dynamic Dialogue Policy for Continual Reinforcement Learning (2022, methodology): “We do not include a baseline based on expert-defined domain-independent features (Wang et al., 2015) as this requires a significant amount of hand-coding and suffers from scalabilility issues.”
Feudal Reinforcement Learning for Dialogue Management in Large Domains (2018, methodology): “The differences with the features used in (Wang et al., 2015) and (Pa-pangelis and Stylianou, 2017) are the following: • No priority or importance features are used.”
Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management (2020, methodology): “Thus, DQNDIP-M ignores the relations among slot-dependent agents.”
Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability (2017, background): “Researchers proposed the idea of extracting slot-value independent statistics as the dialog state (Wang et al., 2015; Gaˇsi´c et al., 2015a), so that the dialog state representation can be shared across systems serving different knowledge sources.”
Dynamic Dialogue Policy Transformer for Continual Reinforcement Learning (2022, methodology): “In the realm of domain adaptation, works assume a fixed number of actions that are slot-independent, and focus on the inclusion of slot-dependent actions when the domain changes (Wang et al., 2015; Casanueva et al., 2018; Chen et al., 2018; Chen et al., 2020; Lin et al., 2021).”
Deep Transfer in Reinforcement Learning by Language Grounding (2017, unknown): “There have been a few attempts at model-based transfer for RL (Taylor et al., 2008; Nguyen et al., 2012; Gaˇsic et al., 2013; Wang et al., 2015) but these methods either rely on hand-coded inter-task mappings for state and actions spaces or require signiﬁcant interactions in the target task to…”