オカダ イサク   岡田 伊策    所属   専修大学  ネットワーク情報学部    職種   特任教授
言語種別	日本語
発行・発表の年月	2014
形態種別	研究論文（学術雑誌）
標題	Technique for searching tabular form documents using metadata harvested by table structure analysis.
執筆形態	共著
掲載誌名	Artificial Intelligence Research
掲載区分	国外
出版社・発行元	Sciedu Press
担当区分	筆頭著者
著者・共著者	◎Isaac Okada, Minoru Saito, Yoshiaki Oida, Hiroyuki Yamato, Kazuo Hiekata, Satoru Nakamura, Naoto Fukada
概要	Conducting full-text searches on collections of tabular files, in which a single sheet corresponds to a single document and each file consists of multiple sheets, typically involves retrieving many candidate files that include the search terms. Therefore, it would be advantageous to enable the pinpointing of desired documents with greater accuracy regardless of the operator’s level of experience. In the present study, we propose a method in which operational classifications are assigned as metadata on the basis of the table structure of a sheet. We obtain the table structure of the sheet and assign metadata based on a set of rules established individually for each pattern in the structure. We propose two methods for representing the table structures obtained: a method using node property matrix, and a method in which positional data regarding cells containing specific operation-description data are indexed.
researchmap用URL	https://doi.org/10.5430/air.v3n1p46