An ISU Dialogue System Exhibiting Reinforcement Learning of Dialogue Policies: Generic Slot-Filling in the TALK In-car System
By Oliver Lemon, Kallirroi Georgila, James Henderson, Matthew N. Stuttle. 2006
128 citations recorded by the source corpus.
We demonstrate a multimodal dialogue system using reinforcement learning for in-car scenarios, developed at Edinburgh University and Cambridge University for the TALK project. This prototype is the first "Information State Update" (ISU) dialogue system to exhibit reinforcement learning of dialogue strategies, and also has a fragmentary clarification feature. This paper describes the main components and functionality of the system, as well as the purposes and future use of the system, and surveys the research issues involved in its construction. Evaluation of this system (i.e. comparing the baseline system with handcoded vs. learnt dialogue policies) is ongoing, and the demonstration will show both.
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
- Jianfeng Gao
- Jason Aaron Edward Weston
- Mohit Bansal
- Yoshua Bengio
- Kyunghyun Cho
- Sergey Levine
- Dhruv Batra
- Percy Liang
In Reinforcement Learning
- Dhruv Batra
- Olivier Pietquin
- Jason Aaron Edward Weston
- Stefan Lee
- Matthieu Geist
- Hervé Frezza-Buet
- José M. F. Moura
- Shikhar Sharma
In Dialogue & Conversational AI
Citations in the corpus
- Learning End-to-End Goal-Oriented Dialog (2016, background): “They are becoming crucial tools in a broad range of applications, from recommendation or news reporting to online shopping, and are likely to play a major role in the future.”
- Frames: a corpus for adding memory to goal-oriented dialogue systems (2017, background): “Much work has focused on spoken dialogue (Lemon and Pietquin, 2007; Walker et al., 1998; Williams and Zweig, 2016), since spoken dialogue systems are useful in many settings, including in hands-free environments such as cars (Lemon et al., 2006).”
- What Should I Ask? Using Conversationally Informative Rewards for Goal-oriented Visual Dialog. (2019, unknown): “Most earlier works made use of a predefined template (Lemon et al., 2006; Wang and Lemon, 2013) to generate dialogues.”
- Entity-Relation Extraction as Multi-Turn Question Answering (2019, background): “This is closely akin to the multi-turn slot filling dialogue system (Williams and Young, 2005; Lemon et al., 2006); (2) the question query encodes important prior information for the relation”
- Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog (2017, background): “While historically such agents have been based on slot filling (Lemon et al., 2006), the dominant paradigm today is neural dialog models (Bordes and Weston, 2016; Weston, 2016; Serban et al.”
- Sample-efficient batch reinforcement learning for dialogue management optimization (2011, methodology): “It is implemented in a state-of-the-art academic dialogue management system, namely the dipper system [Lemon et al. 2006].”
- Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation (2019, background): “Recent advances in deep learning have led an end-to-end neural approach [1–5] to task-oriented dialog problems that can reduce a laborious labeling task on states and intents [6, 7].”