Online learning and transfer for user adaptation in dialogue systems
| Autor: | Olivier Pietquin, Carrara Nicolas, Romain Laroche |
|---|---|
| Přispěvatelé: | Orange Labs [Lannion], France Télécom, Sequential Learning (SEQUEL), Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Maluuba |
| Rok vydání: | 2017 |
| Předmět: |
business.industry
Computer science media_common.quotation_subject 02 engineering and technology Machine learning computer.software_genre [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] Task (project management) Constraint (information theory) Negotiation [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] 020204 information systems Metric (mathematics) 0202 electrical engineering electronic engineering information engineering Benchmark (computing) Reinforcement learning 020201 artificial intelligence & image processing Artificial intelligence business Cluster analysis Adaptation (computer science) computer media_common |
| Zdroj: | SIGDIAL/SEMDIAL joint special session on negotiation dialog 2017 SIGDIAL/SEMDIAL joint special session on negotiation dialog 2017, Aug 2017, Saarbrücken, Germany |
| DOI: | 10.21437/semdial.2017-15 |
| Popis: | International audience; We address the problem of user adaptation in Spoken Dialogue Systems. The goal is to quickly adapt online to a new user given a large amount of dialogues collected with other users. Previous works using Transfer for Reinforcement Learning tackled this problem when the number of source users remains limited. In this paper, we overcome this constraint by clustering the source users: each user cluster, represented by its centroid, is used as a potential source in the state-of-the-art Transfer Reinforcement Learning algorithm. Our benchmark compares several clustering approaches , including one based on a novel metric. All experiments are led on a negotiation dialogue task, and their results show significant improvements over baselines. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|