2012 Fiscal Year Final Research Report

Detecting Document Infringement based on Graph Transformation

Research Project

Project/Area Number	24800049
Research Category	Grant-in-Aid for Research Activity Start-up
Allocation Type	Single-year Grants
Research Field	Intelligent informatics
Research Institution	Kyushu University
Principal Investigator	CHOU Bin-hui 九州大学, システム情報科学研究院, 学術研究員 (50636793)
Co-Investigator(Renkei-kenkyūsha)	SUZUKI Einoshin 九州大学, システム情報科学研究院, 教授 (10251638)
Project Period (FY)	2012
Keywords	侵害検知 / 文書盗作・剽窃 / グラフ変換 / グラフマッチング
Research Abstract	In this research, we tackle the problem of detecting document infringement, which is considered as a severe problem owing to the convenience of Internet. Typical information retrieval methods, stopword-based methods and fingerprinting methods are commonly used to detect infringement by using sequences of words as they appear in the document. As such, they fail to detect infringement when an author reconstructs a source document by re-ordering and re-combining phrases. Because graph structure fits for representing relationships between entities, we propose a novel infringement detection method, in which we use graphs to represent documents by modeling grammatical relationships between words. Experimental results show that our proposed method outperforms two n-gram methods and increases recall values by 10%.

(3 results)