Abstract | ||
---|---|---|
We present a Deep Learning approach to dialogue management for multiple domains. Instead of training multiple models (e.g. one for each domain), we train a single domain-independent policy network that is applicable to virtually any information-seeking domain We use the Deep Q-Network algorithm to train our dialogue policy, and evaluate against simulated and paid human users. The results show that our algorithm outperforms previous approaches while being more practical and scalable. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/978-3-319-92108-2_9 | Lecture Notes in Electrical Engineering |
Keywords | DocType | Volume |
Spoken dialogue system,Multi domain,Deep learning,Dialogue policy learning | Conference | 510 |
ISSN | Citations | PageRank |
1876-1100 | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alexandros Papangelis | 1 | 93 | 18.01 |
Yannis Stylianou | 2 | 1436 | 140.45 |