- Abstract:
- 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 hadcoded vs. learnt dialogue policies) is ongoing, and the demonstration will show both.
- Links To Paper
- 1st link
- Bibtex format
- @InProceedings{EDI-INF-RR-1117,
- author = {
Oliver Lemon
and Kallirroi Georgila
and James Henderson
and Matthew Stuttle
},
- title = {An ISU dialogue system exhibiting reinforcement learning of dialogue policies: generic slot-filling in the TALK in-car system},
- book title = {11th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2006)},
- year = 2006,
- url = {http://acl.ldc.upenn.edu/E/E06/E06-2009.pdf},
- }
|
