@inproceedings{tannier-2014-extracting,
title = "Extracting News Web Page Creation Time with {DCTF}inder",
author = "Tannier, Xavier",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/3_Paper.pdf",
pages = "2037--2042",
abstract = "Web pages do not offer reliable metadata concerning their creation date and time. However, getting the document creation time is a necessary step for allowing to apply temporal normalization systems to web pages. In this paper, we present DCTFinder, a system that parses a web page and extracts from its content the title and the creation date of this web page. DCTFinder combines heuristic title detection, supervised learning with Conditional Random Fields (CRFs) for document date extraction, and rule-based creation time recognition. Using such a system allows further deep and efficient temporal analysis of web pages. Evaluation on three corpora of English and French web pages indicates that the tool can extract document creation times with reasonably high accuracy (between 87 and 92{\%}). DCTFinder is made freely available on \url{http://sourceforge.net/projects/dctfinder/}, as well as all resources (vocabulary and annotated documents) built for training and evaluating the system in English and French, and the English trained model itself.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tannier-2014-extracting">
<titleInfo>
<title>Extracting News Web Page Creation Time with DCTFinder</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xavier</namePart>
<namePart type="family">Tannier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Web pages do not offer reliable metadata concerning their creation date and time. However, getting the document creation time is a necessary step for allowing to apply temporal normalization systems to web pages. In this paper, we present DCTFinder, a system that parses a web page and extracts from its content the title and the creation date of this web page. DCTFinder combines heuristic title detection, supervised learning with Conditional Random Fields (CRFs) for document date extraction, and rule-based creation time recognition. Using such a system allows further deep and efficient temporal analysis of web pages. Evaluation on three corpora of English and French web pages indicates that the tool can extract document creation times with reasonably high accuracy (between 87 and 92%). DCTFinder is made freely available on http://sourceforge.net/projects/dctfinder/, as well as all resources (vocabulary and annotated documents) built for training and evaluating the system in English and French, and the English trained model itself.</abstract>
<identifier type="citekey">tannier-2014-extracting</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/3_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2037</start>
<end>2042</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extracting News Web Page Creation Time with DCTFinder
%A Tannier, Xavier
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F tannier-2014-extracting
%X Web pages do not offer reliable metadata concerning their creation date and time. However, getting the document creation time is a necessary step for allowing to apply temporal normalization systems to web pages. In this paper, we present DCTFinder, a system that parses a web page and extracts from its content the title and the creation date of this web page. DCTFinder combines heuristic title detection, supervised learning with Conditional Random Fields (CRFs) for document date extraction, and rule-based creation time recognition. Using such a system allows further deep and efficient temporal analysis of web pages. Evaluation on three corpora of English and French web pages indicates that the tool can extract document creation times with reasonably high accuracy (between 87 and 92%). DCTFinder is made freely available on http://sourceforge.net/projects/dctfinder/, as well as all resources (vocabulary and annotated documents) built for training and evaluating the system in English and French, and the English trained model itself.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/3_Paper.pdf
%P 2037-2042
Markdown (Informal)
[Extracting News Web Page Creation Time with DCTFinder](http://www.lrec-conf.org/proceedings/lrec2014/pdf/3_Paper.pdf) (Tannier, LREC 2014)
ACL