Publication Details

Information Extraction from the Web by Matching Visual Presentation Patterns

BURGET Radek. Information Extraction from the Web by Matching Visual Presentation Patterns. In: Knowledge Graphs and Language Technology: ISWC 2016 International Workshops: KEKI and NLP&DBpedia. Lecture Notes in Computer Science vol. 10579. Kobe: Springer International Publishing, 2017, pp. 10-26. ISBN 978-3-319-68722-3. Available from: https://link.springer.com/chapter/10.1007/978-3-319-68723-0_2
Czech title
Extrakce informací z webu založená na vyhledávání prezentačních vzorů
Type
conference paper
Language
english
Authors
URL
Keywords

web data integration, information extraction, structured record extraction, page segmentation, content classification, ontology mapping

Abstract

The documents available in the World Wide Web contain large amounts of information presented in tables, lists or other visually regular structures. The published information is however usually not annotated explicitly or implicitly and its interpretation is left on a human reader. This makes the information extraction from web documents a challenging problem. Most existing approaches are based on a top-down approach that proceeds from the larger page regions to individual data records, which depends on different heuristics. We present an opposite bottom-up approach. We roughly identify the smallest data fields in the document and later, we refine this approximation by matching the discovered visual presentation patterns with the expected semantic structure of the extracted information. This approach allows to efficiently extract structured data from heterogeneous documents without any kind of additional annotations as we demonstrate experimentally on various application domains.

Published
2017
Pages
10-26
Proceedings
Knowledge Graphs and Language Technology: ISWC 2016 International Workshops: KEKI and NLP&DBpedia
Series
Lecture Notes in Computer Science vol. 10579
Conference
The 15th International Semantic Web Conference, Kobe, JP
ISBN
978-3-319-68722-3
Publisher
Springer International Publishing
Place
Kobe, JP
DOI
UT WoS
000535971000002
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB11218,
   author = "Radek Burget",
   title = "Information Extraction from the Web by Matching Visual Presentation Patterns",
   pages = "10--26",
   booktitle = "Knowledge Graphs and Language Technology: ISWC 2016 International Workshops: KEKI and NLP\&DBpedia",
   series = "Lecture Notes in Computer Science vol. 10579",
   year = 2017,
   location = "Kobe, JP",
   publisher = "Springer International Publishing",
   ISBN = "978-3-319-68722-3",
   doi = "10.1007/978-3-319-68723-0\_2",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11218"
}
Files
Back to top