Conference paperMILIČKA Martin and BURGET Radek. Information Extraction from Web Sources based on Multi-aspect Content Analysis. In: Semantic Web Evaluation Challenges, SemWebEval 2015 at ESWC 2015. Portorož: Springer International Publishing, 2015, pp. 81-92. ISBN 978-3-319-25517-0. ISSN 1865-0929. | Publication language: | english |
---|
Original title: | Information Extraction from Web Sources based on Multi-aspect Content Analysis |
---|
Title (cs): | Extrakce informací z webových zdrojů založená na více aspektové analýze obsahu |
---|
Pages: | 81-92 |
---|
Proceedings: | Semantic Web Evaluation Challenges, SemWebEval 2015 at ESWC 2015 |
---|
Conference: | 12th Extended Semantic Web Conference 2015 |
---|
Series: | Communications in Computer and Information Science |
---|
Place: | Portorož, SI |
---|
Year: | 2015 |
---|
ISBN: | 978-3-319-25517-0 |
---|
Journal: | Communications in Computer and Information Science, Vol. 2015, No. 548, Heidelberg, DE |
---|
ISSN: | 1865-0929 |
---|
Publisher: | Springer International Publishing |
---|
Files: | |
---|
| Keywords |
---|
document modeling, information extraction, page segmentation, content classifi cation, ontology, RDF |
Annotation |
---|
Information extraction from web pages is often recognized as a
dicult task mainly due to the loose structure and insucient semantic
annotation of their HTML code. Since the web pages are primarily created
for being viewed by human readers, their authors usually do not pay
much attention to the structure and even validity of the HTML code
itself. The CEUR Workshop Proceedings pages are a good illustration of
this. Their code varies from an invalid HTML markup to fully valid and
semantically annotated documents while preserving a kind of uni ed
visual presentation of the contents. In this paper, as a contribution to
the ESWC 2015 Semantic Publishing Challenge, we present an information
extraction approach based on analyzing the rendered pages rather than
their code. The documents are represented by an RDF-based model that
allows to combine the results of di fferent page analysis methods such as
layout analysis and the visual and textual feature classi cation. This
allows to specify a set of generic rules for extracting a particular
information from the page independently on its code. |
BibTeX: |
---|
@INPROCEEDINGS{
author = {Martin Mili{\v{c}}ka and Radek Burget},
title = {Information Extraction from Web Sources based on
Multi-aspect Content Analysis},
pages = {81--92},
booktitle = {Semantic Web Evaluation Challenges, SemWebEval 2015 at ESWC
2015},
series = {Communications in Computer and Information Science},
journal = {Communications in Computer and Information Science},
volume = {2015},
number = {548},
year = {2015},
location = {Portoro{\v{z}}, SI},
publisher = {Springer International Publishing},
ISBN = {978-3-319-25517-0},
ISSN = {1865-0929},
language = {english},
url = {http://www.fit.vutbr.cz/research/view_pub.php.en.iso-8859-2?id=10840}
} |
|