Sample-Based Collection and Adjustment Algorithm for Metadata Extraction Parameter of Flexible Format Document

Autor:	Toshiko Matsumoto, Takashi Onoyama, Mitsuharu Oba
Rok vydání:	2010
Předmět:	Metadata Data element Information retrieval Basis (linear algebra) Computer science Keyword extraction Extraction (military) Sample (statistics) Data mining computer.software_genre Algorithm computer Metadata repository
Zdroj:	Artifical Intelligence and Soft Computing ISBN: 9783642132315 ICAISC (2)
DOI:	10.1007/978-3-642-13232-2_69
Popis:	We propose an algorithm for automatically generating metadata extraction parameters. It first enumerates candidates on the basis of metadata occurrence in training documents, and then examines these candidates to avoid side effects and to maximize effectiveness. This two-stage approach enables both avoidance of exponential explosion of computation and detailed optimization. An experiment on Japanese business documents shows that an automatically generated parameter enables metadata extraction as accurately as a manually adjusted one.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::4017ffaa76a08a2781225f2bbbf58969 https://doi.org/10.1007/978-3-642-13232-2_69 Zobrazit plný text záznamu