Automatic optimization of dialogue management

Autor: Michael S. Kearns, Diane J. Litman, Marilyn A. Walker, Satinder Singh
Rok vydání: 2000
Předmět:
Zdroj: COLING
DOI: 10.3115/990820.990893
Popis: Designing the dialogue strategy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a dialogue strategy that addresses the technical challenges in applying reinforcement learning to a working dialogue system with human users. We then show that our approach measurably improves performance in an experimental system.
Databáze: OpenAIRE