Keyword extraction device, keyword extraction method, and computer-readable recording medium storing keyword extraction program

Abstract

Abstract Translated from Japanese (57)【要約】 【課題】 従来の自動キーワード抽出は、処理対象文中 の文字列をそのままキーワードとして文書に索引づけす るため、異表記に対処した検索が不可能である。 【解決手段】 正表記と異表記を共に表記した専門語が 格納された専門語格納手段と一般的で使用頻度の高い基 本語が格納された基本語格納手段を備え、専門語分割点 設定手段で入力文章中の、専門語格納手段にある専門語 の範囲を切り出し、この専門語が、異表記の場合、正表 記置換手段で正表記に置換し、字種分割点設定手段で、 入力文章中の字種の違いを検出し、基本語分割点設定手 段で入力された文章中で基本語格納手段中の基本語の範 囲を切り出し、専門語分割点設定手段と字種分割点設定 手段及び基本語分割点設定手段によって設定された分割 点から部分文字列をキーワードとして切り出す部分文字 列切出手段を備えた。 (57) [Summary] [Problem] In conventional automatic keyword extraction, a character string in a sentence to be processed is indexed as a keyword as it is in a document, so that it is impossible to perform a search that copes with a different notation. SOLUTION: There is provided a technical term storage means for storing a technical term in which both a normal notation and a different notation are written, and a basic word storage means for storing a general and frequently used basic word, and a technical term division point setting means. In the input sentence, cut out the range of technical terms in the technical term storage means, and if this technical term is a different notation, replace it with regular notation by regular notation replacement means, and in the character type division point setting means, Detect differences in character types in the input sentence, cut out the range of basic words in the basic word storage means in the sentence input by the basic word division point setting means, and set up technical word division point setting means and character type division points Means for extracting a partial character string as a keyword from the division point set by the means and the basic word division point setting means.

Inventors

• 👤 Yamahiko Ito
• 👤 山彦 伊藤
• 👤 泰博 ▲高▼山
• 👤 Yasuhiro Takayama
• 👤 Katsushi Suzuki
• 👤 克志 鈴木

Bibliographic Details