Extraction of Context-Sensitive Meaning of Japanese Onomatopoeic Expressions Using Kansei Polarities

カテゴリ: 研究会(論文単位)

論文No: IS11027

グループ名: 【C】電子・情報・システム部門 情報システム研究会

発行日: 2011/04/16

タイトル(英語): Extraction of Context-Sensitive Meaning of Japanese Onomatopoeic Expressions Using Kansei Polarities

著者名: Hashimoto Kiyota(Osaka Prefecture University),Kitanaka Yuki(Osaka Electro-Communication University),Takeuchi Kazuhiro(Osaka Electro-Communication University)

著者名(英語): Hashimoto Kiyota(Osaka Prefecture University),Kitanaka Yuki(Osaka Electro-Communication University),Takeuchi Kazuhiro(Osaka Electro-Communication University)

キーワード: Ｏｎｏｍａｔｏｐｏｅｉｃ　ｅｘｐｒｅｓｓｉｏｎ　ｉｎ　Ｊａｐａｎｅｓｅ|Ｋａｎｓｅｉ　ｐｏｌａｒｉｔｙ|ｃｏｎｔｅｘｔ－ｓｅｎｓｉｔｉｖｅ　ｍｅａｎｉｎｇ|ａｕｔｏｍａｔｉｃ　ｅｘｔｒａｃｔｉｏｎ|ｓｅｎｓｅ　ｄｉｆｆｅｒｅｎｔｉａｔｉｏｎ|Onomatopoeic expression in Japanese|Kansei polarity|context-sensitive meaning|automatic extraction|sense differentiation

要約(日本語): Onomatopoeic expressions are frequently used in Japanese but, as well as other types of subjective adjectival and adverbial expressions, their Kansei evaluative value, or their Kansei polarity, depends on genre and context and is difficult to describe, let alone their exact meaning. In this study, an automatic extraction method of Kansei polarities of Japanese onomatopoeic expressions according to genre and context is proposed. It uses the contrastive use of pair expressions with seemingly opposite Kansei polarities in different genres and contexts, and extracts their feature vectors.

要約(英語): Onomatopoeic expressions are frequently used in Japanese but, as well as other types of subjective adjectival and adverbial expressions, their Kansei evaluative value, or their Kansei polarity, depends on genre and context and is difficult to describe, let alone their exact meaning. In this study, an automatic extraction method of Kansei polarities of Japanese onomatopoeic expressions according to genre and context is proposed. It uses the contrastive use of pair expressions with seemingly opposite Kansei polarities in different genres and contexts, and extracts their feature vectors.

原稿種別: 日本語

PDFファイルサイズ: 534 Kバイト