Transactions of the Japanese Society for Artificial Intelligence
Online ISSN : 1346-8030
Print ISSN : 1346-0714
ISSN-L : 1346-0714
Original Paper
Open Domain Monologue Generation for Speaking-oriented Dialogue Systems
Michimasa InabaYuka YoshinoKenichi Takahashi
Author information

2016 Volume 31 Issue 1 Pages DSF-F_1-9


This paper presents an open domain monologue generation method for non-task-oriented dialogue systems to be able to speak their opinions and impressions as a speaker. To generate monologues, we acquire suitable utterances that contain a given topic from Twitter. Our method determines whether utterances have cohesion or not using the support vector machine and concatenate them in a row. It scores the utterance sequences from the aspect of their humor, unexpectedness and speciality in the given topic. We acquire the utterance sequences that ranks high as monologues. Results of an experiment demonstrate that our method can generate amusing and semantically appropriate monologues.

Content from these authors
© The Japanese Society for Artificial Intelligence 2016
Previous article Next article