Title:
スコアリングモデル生成装置、学習データ生成装置、検索システム、スコアリングモデル生成方法、学習データ生成方法、検索方法及びそのプログラム
Document Type and Number:
Japanese Patent JP5700566
Kind Code:
B2
Abstract:
PROBLEM TO BE SOLVED: To provide a learning data generation device generating learning data used when learning a scoring model on the basis of statistical model learning.SOLUTION: The learning data generation device is provided with a plurality of documents and generates learning data that is used when learning a scoring model in a document retrieval on the basis of the statistical model learning. Word string generation means generates, for each document to be provided, one or more word strings including a word included in the document. Learning data generation means defines each of the generated word strings and a label indicating the document used when generating the word string as a query and a reference respectively and defines a set of the query and the reference as learning data.
Inventors:
Takanobu Ohba
Takaaki Hori
Atsushi Nakamura
Akinori Ito
Takaaki Hori
Atsushi Nakamura
Akinori Ito
Application Number:
JP2012023886A
Publication Date:
April 15, 2015
Filing Date:
February 07, 2012
Export Citation:
Assignee:
Nippon Telegraph and Telephone Corporation
Tohoku University
Tohoku University
International Classes:
G06F17/30
Domestic Patent References:
| JP2005316953A | ||||
| JP2009259250A | ||||
| JP2010033377A | ||||
| JP2004046775A | ||||
| JP2009157442A | ||||
| JP2009238235A | ||||
| JP2010128774A | ||||
| JP2004046621A |
Foreign References:
| US20070179949 | ||||
| US20070203908 | ||||
| US20110314011 | ||||
| US20110191310 |
Other References:
清水 徹,Web検索における検索結果ランキング ~評価手法とアルゴリズム~,知能と情報,日本知能情報ファジィ学会,2010年 4月15日,第22巻,第2号,page 223-229
土田 正明,辞書とタグ無しコーパスを用いた固有表現抽出器の学習法,2009年度人工知能学会全国大会(第23回)論文集 [CD-ROM],2009年 7月10日,page 1-4
土田 正明,辞書とタグ無しコーパスを用いた固有表現抽出器の学習法,2009年度人工知能学会全国大会(第23回)論文集 [CD-ROM],2009年 7月10日,page 1-4
Attorney, Agent or Firm:
Naoki Nakao
Yukio Nakamura
Yoshimura Munehiro
Yukio Nakamura
Yoshimura Munehiro