@inproceedings{weiser-etal-2008-automatic,
title = "Automatic Identification of Temporal Information in Tourism Web Pages",
author = "Weiser, St{\'e}phanie and
Laublet, Philippe and
Minel, Jean-Luc",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/44_paper.pdf",
abstract = "This paper presents our work on the detection of temporal information in web pages. The pages examined within the scope of this study were taken from the tourism sector and the temporal information in question is thus particular to this area. The differences that exist between extraction from plain textual data and extraction from the web are brought to light. These differences mainly concern the spatial arrangement of the text, the use of punctuation and the respect of traditional syntactic rules. The temporal expressions to be extracted are classified into two kinds: temporal information that concerns one particular event and repetitive temporal information. We adopt a symbolic approach relying on patterns and rules for the detection, extraction and annotation of temporal expressions; our method is based on the use of transducers. First evaluations have shown promising results. Since the visual structure of a web page is very important and often informs the user before he has even read the text, a semiotic study is also presented in this paper.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weiser-etal-2008-automatic">
<titleInfo>
<title>Automatic Identification of Temporal Information in Tourism Web Pages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stéphanie</namePart>
<namePart type="family">Weiser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Laublet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Luc</namePart>
<namePart type="family">Minel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our work on the detection of temporal information in web pages. The pages examined within the scope of this study were taken from the tourism sector and the temporal information in question is thus particular to this area. The differences that exist between extraction from plain textual data and extraction from the web are brought to light. These differences mainly concern the spatial arrangement of the text, the use of punctuation and the respect of traditional syntactic rules. The temporal expressions to be extracted are classified into two kinds: temporal information that concerns one particular event and repetitive temporal information. We adopt a symbolic approach relying on patterns and rules for the detection, extraction and annotation of temporal expressions; our method is based on the use of transducers. First evaluations have shown promising results. Since the visual structure of a web page is very important and often informs the user before he has even read the text, a semiotic study is also presented in this paper.</abstract>
<identifier type="citekey">weiser-etal-2008-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/44_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Identification of Temporal Information in Tourism Web Pages
%A Weiser, Stéphanie
%A Laublet, Philippe
%A Minel, Jean-Luc
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F weiser-etal-2008-automatic
%X This paper presents our work on the detection of temporal information in web pages. The pages examined within the scope of this study were taken from the tourism sector and the temporal information in question is thus particular to this area. The differences that exist between extraction from plain textual data and extraction from the web are brought to light. These differences mainly concern the spatial arrangement of the text, the use of punctuation and the respect of traditional syntactic rules. The temporal expressions to be extracted are classified into two kinds: temporal information that concerns one particular event and repetitive temporal information. We adopt a symbolic approach relying on patterns and rules for the detection, extraction and annotation of temporal expressions; our method is based on the use of transducers. First evaluations have shown promising results. Since the visual structure of a web page is very important and often informs the user before he has even read the text, a semiotic study is also presented in this paper.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/44_paper.pdf
Markdown (Informal)
[Automatic Identification of Temporal Information in Tourism Web Pages](http://www.lrec-conf.org/proceedings/lrec2008/pdf/44_paper.pdf) (Weiser et al., LREC 2008)
ACL