|
Accession number;05A0661035
|
| Title;Ontology Extraction from Tables |
| Author;
TANAKA MASAHIRO
(Kyoto Univ., JPN)
ISHIDA TOORU
(Kyoto Univ., JPN)
|
Journal Title;Proceedings of the Annual Conference on JSAI (CD-ROM)
|
Journal Code:X0580B
|
ISSN:
|
|
VOL.19th;NO.;PAGE.1A4-02(2005)
|
| Figure&Table&Reference;FIG.7, TBL.3, REF.3 |
| Pub. Country;Japan |
| Language;Japanese |
| Abstract;Previous works on information extraction from tables make use of lexical knowledge bases of tables or prior knowledge such as a cognition model of tables. However, we often need to interpret table structures in each table differently and to treat lexicons in various domains for processing a broad range of tables on the Web. The method proposed in this paper extracts an ontology from a table by using relations represented by structures. Once the interpretations of table structures are given by humans, the table structures are automatically generalized to extract relations from the whole table. We defined a formal representation of generalized table structures based on the adjacency of cells and iterative structures. Our experiments showed that the method extracted class-hierarchies, property-value pairs and other various relations from the tables containing price lists, contact lists and statistics on the Web. (author abst.) |
|
|
|
Related Articles;
|
