A statistical prediction model of speakers%26apos; intentions using multi-level features in a goal-oriented dialog system

作者：Seon Choong Nyoung; Kim Harksoo^*; Seo Jungyun

来源：Pattern Recognition Letters, 2012, 33(10): 1397-1404.

DOI：10.1016/j.patrec.2012.02.018

• Speech act prediction
• Concept sequence prediction
• Multi-level feature

A dialog system is an intelligent program that helps users easily access information stored in a knowledge base by formulating requests in their natural language. A dialog system needs an intention prediction module for use as a preprocessor to reduce the search space of an automatic speech recognizer. To satisfy these needs, we propose a statistical model to predict speakers%26apos; intentions. The proposed model represents a dialog history, with various levels of linguistic features. The proposed model predicts the user%26apos;s next intention by giving the linguistic features as inputs to a statistical machine learning model. In experiments conducted in a schedule management domain, the proposed model showed a higher average precision than the previous model.

• 出版日期2012-7-15