When Your Users Are Not Serious : Using Web-based Associations, Affect and Humor for Generating Appropriate Utterances for Inappropriate Input
スポンサーリンク
概要
- 論文の詳細を見る
In this paper we propose a method for generating simple but semantically correct replies to user inputs which are not related to a given task of a task-oriented information kiosk or any other natural language interface placed in a public place. We describe our method for retrieving meaningful associations from the Web and adding modality based on chatlog data. After showing the results of the evaluation experiments, we introduce an implementation of an affect analysis algorithm and pun generator to increase users satisfaction level.
著者
-
PTASZYNSKI Michal
Hokkaido University, Graduate School of Information Science and Technology
-
DYBALA Pawel
Hokkaido University, Graduate School of Information Science and Technology
-
RZEPKA Rafal
Hokkaido University, Graduate School of Information Science and Technology
-
ARAKI Kenji
Hokkaido University, Graduate School of Information Science and Technology
-
Higuchi Shinsuke
Hokkaido University
関連論文
- When Your Users Are Not Serious : Using Web-based Associations, Affect and Humor for Generating Appropriate Utterances for Inappropriate Input
- A system for affect analysis of utterances in Japanese supported with Web mining (特集 感性検索)
- An automatic evaluation method for conversational agents based on Affect-as-Information Theory (特集 感情)
- When Your Users Are Not Serious : Using Web-based Associations, Affect and Humor for Generating Appropriate Utterances for Inappropriate Input
- Study on parameters of the variable threshold to detect local speech rate deceleration in Japanese spontaneous conversational speech