Implementation of an Integrated System for Editing Meta Data Using Machine Learning Techniques

2014 Fiscal Year Final Research Report

• Project/Area Number: 24300097
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Library and information science/Humanistic social informatics
• Research Institution: National Institute of Informatics
• Principal Investigator: ADACHI Jun 国立情報学研究所, コンテンツ科学研究系, 教授 (80143551)
• Co-Investigator(Kenkyū-buntansha): OHTA Manabu 岡山大学, 自然科学研究科, 教授 (10326019)
• Co-Investigator(Renkei-kenkyūsha): TAKASU Atsuhiro 国立情報学研究所, コンテンツ科学研究系, 教授 (90216648)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 書誌パージング / メタデータ / コーパス / CRF / 機関リポジトリ / テキストマイニング

Outline of Final Research Achievements

The purpose of this study is to implement a system which extracts meta data from digital documents to edit and identify the meta data accurately by matching against other databases as an integrated environment for editing such meta data. We proposed accurate and inexpensive methods to extract bibliographic and citation information as meta data from research papers of which the layout was analyzed. We also created several reference string corpora of research papers by annotating the reference strings with bibliographic information for evaluating bibliographic information extraction methods.

Free Research Field

情報工学