HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
情報科学研究科  >
雑誌発表論文等  >

Naturalness of an Utterance Based on the Automatically Retrieved Commonsense

post-0490.pdf100.55 kBPDF見る/開く

タイトル: Naturalness of an Utterance Based on the Automatically Retrieved Commonsense
著者: Rafal, Rzepka 著作を一覧する
Yali, Ge 著作を一覧する
Kenji, Araki 著作を一覧する
発行日: 2005年
出版者: IJCAI
誌名: 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.
資料タイプ: proceedings
出現コレクション:雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

提供者: Rafal Rzepka


本サイトに関するご意見・お問い合わせは repo at へお願いします。 - 北海道大学