Statistical Responce Method for Non-task-oriented Dialogue Agent

Michimasa INABA  Naoki HIRAI  Fujio TORIUMI  Kenichiro ISHII  

Publication
D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition)   Vol.J95-D   No.6   pp.1390-1400
Publication Date: 2012/06/01
Online ISSN: 1881-0225
DOI: 
Print ISSN: 1880-4535
Type of Manuscript: PAPER
Category: 
Keyword: 
dialogue agent,  non-task-oriented,  learning to rank,  

Full Text(in Japanese): PDF(537KB)>>
Buy this Article




Summary: 
Computerized dialogue agents have recently been actively investigated in various fields. There is a great demand not only for task-oriented dialogue agents such as reservation services but also for non-task-oriented ones such as chatbots. This paper presents a statistical responce method for non-task-oriented dialogue agents based on learning to rank. Learning to rank is a statistical learning technology for sorting objects. Our method ranks candidate utterances which are prepared beforehand, in order of suitability for a response, and selects the top utterance.