Policy committee for adaptation in multi-domain spoken dialogue systems

By Milica Gasic, Nikola Mrksic, Pei-hao Su, David Vandyke, Tsung-Hsien Wen, Susannah Young. 2015

66 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Reinforcement Learning, Dialogue & Conversational AI

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

1. Jianfeng Gao
2. Minlie Huang
3. Bing Liu
4. Lihong Li
5. Maxine Eskénazi
6. Paweł Budzianowski
7. Baolin Peng
8. Xiujun Li

In Reinforcement Learning

1. Jianfeng Gao
2. Lihong Li
3. Paweł Budzianowski
4. Maxine Eskénazi
5. Tiancheng Zhao
6. Xiujun Li
7. Pei-hao Su
8. Baolin Peng

In Dialogue & Conversational AI

1. Minlie Huang
2. Pei-hao Su
3. Tiancheng Zhao
4. Stefan Ultes
5. Paweł Budzianowski
6. Maxine Eskénazi
7. Milica Gasic
8. Jianfeng Gao

Citations in the corpus

• Dynamic Dialogue Policy for Continual Reinforcement Learning (2022, methodology): “Gašić et al. (2015) use a committee of Gaussian processes together with designed kernel functions in order to define these similarities and therefore allow domain extension and training on new domains.”
• Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning (2017, background): “This requirement makes most of the existing methods of learning multi-domain dialogue agents (Cuay´ahuitl, 2009; Gasic et al., 2015b) inapplicable: these methods train a collection of policies, one for each domain, and there is no cross-domain constraints required to successfully complete a…”
• Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog (2019, background): “A natural way to handle multi-domain dialog systems is to learn multiple independent singledomain sub-policies (Wang et al., 2014; Gašić et al., 2015; Cuayáhuitl et al., 2016).”
• Feudal Reinforcement Learning for Dialogue Management in Large Domains (2018, methodology): “Space abstraction, instead, has been successfully applied to dialogue tasks such as Dialogue State Tracking (DST) (Henderson et al., 2014b), and policy transfer between domains (Gaˇsi´c et al., 2013, 2015; Wang et al., 2015).”
• 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): “Gaši´c et al. (2015) use a committee of Gaussian processes together with designed kernel functions in order to define these similarities and therefore allow domain extension and training on new domains.”