Naturalness of an Utterance Based on the Automatically Retrieved Commonsense

Rzepka, Rafal; Ge, Yali; Araki, Kenji

Proceedings of IJCAI 2005 - Nineteenth International Joint Conference on Artificial Intelligence, 2005

Permalink : https://hdl.handle.net/2115/63621

このアイテムのアクセス数:568件（2026-10-11 21:36 集計）

ファイル	フォーマット	サイズ	閲覧回数	説明
ost-0490	pdf	100 KB	401

アクセス権	open access
URI	https://hdl.handle.net/2115/63621
タイトル	Naturalness of an Utterance Based on the Automatically Retrieved Commonsense
著者	Rzepka, Rafal ; Ge, Yali ; Araki, Kenji
e-Rad_Researcher 80396316 著者名 Rzepka, Rafal
著者名 Ge, Yali
著者名 Araki, Kenji
言語	英語
発行日	2005
出版者	IJCAI
収録物名	Proceedings of IJCAI 2005 - Nineteenth International Joint Conference on Artificial Intelligence
抄録	In this research we investigated user’s behavior while facing a system coping with common knowledge about keywords and compared it with not only classic word-spotting method but also with random text-mining. We show how even a simple implementation of our idea can enrich the conversation and increase the naturalness of computer’s utterances. Our results show that even very commonsensical utterances are more natural than classic approaches and also methods we developed to make a conversation more interesting. For arousing opinion exchange during the session, we will also briefly introduce our idea of combining latest NLP achievements into one holistic system where the main engine we want to base on commonsense processing and affective computing.
会議記述	会議名 International Joint Conference on Artificial Intelligence 回次 19 開催地 Edinburgh, Scotland 開催国 United Kingdom of Great Britain and Northern Ireland
資源タイプ	会議発表論文
出版タイプ	Version of Record