Title :
Experiments Study for Scientific Texts Domain Keyword Acquisition
Author :
Luo, Xiangfeng ; Fang, Ning ; Xu, Weimin ; Yu, Sheng ; Yan, Kai ; Xiao, Huizhe
Author_Institution :
Semantic Grid & Web Content Anal. Group, Shanghai Univ., Shanghai, China
Abstract :
Scientific texts domain keyword is one of the basic elements of the text high-level semantics acquisition, domain ontology building and the knowledge representation in semantic grid, knowledge grid and escience environment. It is also the indispensable foundation and prerequisite work of Web scientific texts automatic classification, clustering and personalized services. TFIDF based TDDF formula is proposed to extract scientific texts domain keyword. The experiments proved that TDDF formula extracting texts domain keyword is superior to the classic TFIDF formula does. Above discussions and achievements can provide certain support not only for the establishment of semantic grid, knowledge grid and escience environment, but also for the Web knowledge acquisition, representation and text information retrieval and so on.
Keywords :
grid computing; information retrieval; knowledge acquisition; ontologies (artificial intelligence); pattern clustering; scientific information systems; semantic Web; text analysis; TDDF; TFIDF; Web knowledge acquisition; Web scientific text automatic classification; domain ontology; e-science environment; knowledge grid; knowledge representation; personalized service; scientific text domain keyword extraction; semantic acquisition; semantic grid; text clustering; text information retrieval; Domain keyword; Knowledge Acquisition; Knowledge Grid; Semantic Grid;
Conference_Titel :
Semantics, Knowledge and Grid, 2006. SKG '06. Second International Conference on
Conference_Location :
Guilin
Print_ISBN :
0-7695-2673-X
DOI :
10.1109/SKG.2006.50
