HRI-JPホーム > 研究活動 > 論文検索 > Question Selection based on Expected Utility to Acquire Information through Dialogue

研究活動

論文検索

Advanced Search

January 2017

Question Selection based on Expected Utility to Acquire Information through Dialogue

  • K. Komatani, T. Otsuka, S. Sato, M. Nakano,
  • in Dialogues with Social Robots,
  • no. 427,
  • K. Jokinen, G. Wilcock Eds,
  • Springer,
  • 2017,
  • pp. 79-91,
  • Chapter in a collection

We have been developing a method for a dialogue system to acquire information (e.g., cuisines of unknown restaurants) through dialogue by asking questions of the users. It is important that the questions are concise and concrete to prevent users from being annoyed. Our method selects the most appropriate question on the basis of expected utility calculated for four types of question: Yes/No, alternative, 3-choice, and Wh- questions.We define utility values for the four types by consider- ing their length and potential damage in the case of wrong questions and also derive the probability representing how likely each question is to contain a correct cuisine. The expected utility is then calculated as the sum totals of the products of the utility and the probability. We empirically compare several ways to integrate two previ- ously proposed basic confidence measures (CMs) when deriving the probability for each question. We also examine the appropriateness of the utility values through questionnaires administered to 15 participants.

Search by Other Conditions

Keywords
Entry type
Years
to
Authors
Language
Refereed