その他 (国際)Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems

Satoshi Akasaki(U. Tokyo) andNobuhiro Kaji

arXiv.org

2017.5.4

Recently emerged intelligent assistants on smartphones and homeelectronics (e.g., Siri and Alexa) can be seen as novel hybrids ofdomain-specific task-oriented spoken dialogue systems and open-domainnon-task-oriented ones. To realize such hybrid dialogue systems, this paperinvestigates determining whether or not a user is going to have a chat withthe system. To address the lack of benchmark datasets for this task, weconstruct a new dataset consisting of 15; 160 utterances collected from thereal log data of a commercial intelligent assistant (and will release thedataset to facilitate future research activity). In addition, we investigateusing tweets and Web search queries for handling open-domain userutterances, which characterize the task of chat detection. Experimentsdemonstrated that, while simple supervised methods are effective, the use ofthe tweets and search queries further improves the F1-score from 86.21 to87.53.

Paper :Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems（外部サイト）