@inproceedings{strotgen-gertz-2012-temporal,
title = "Temporal Tagging on Different Domains: Challenges, Strategies, and Gold Standards",
author = {Str{\"o}tgen, Jannik and
Gertz, Michael},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/425_Paper.pdf",
pages = "3746--3753",
abstract = "In the last years, temporal tagging has received increasing attention in the area of natural language processing. However, most of the research so far concentrated on processing news documents. Only recently, two temporal annotated corpora of narrative-style documents were developed, and it was shown that a domain shift results in significant challenges for temporal tagging. Thus, a temporal tagger should be aware of the domain associated with documents that are to be processed and apply domain-specific strategies for extracting and normalizing temporal expressions. In this paper, we analyze the characteristics of temporal expressions in different domains. In addition to news- and narrative-style documents, we add two further document types, namely colloquial and scientific documents. After discussing the challenges of temporal tagging on the different domains, we describe some strategies to tackle these challenges and describe their integration into our publicly available temporal tagger HeidelTime. Our cross-domain evaluation validates the benefits of domain-sensitive temporal tagging. Furthermore, we make available two new temporally annotated corpora and a new version of HeidelTime, which now distinguishes between four document domain types.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strotgen-gertz-2012-temporal">
<titleInfo>
<title>Temporal Tagging on Different Domains: Challenges, Strategies, and Gold Standards</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jannik</namePart>
<namePart type="family">Strötgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Gertz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the last years, temporal tagging has received increasing attention in the area of natural language processing. However, most of the research so far concentrated on processing news documents. Only recently, two temporal annotated corpora of narrative-style documents were developed, and it was shown that a domain shift results in significant challenges for temporal tagging. Thus, a temporal tagger should be aware of the domain associated with documents that are to be processed and apply domain-specific strategies for extracting and normalizing temporal expressions. In this paper, we analyze the characteristics of temporal expressions in different domains. In addition to news- and narrative-style documents, we add two further document types, namely colloquial and scientific documents. After discussing the challenges of temporal tagging on the different domains, we describe some strategies to tackle these challenges and describe their integration into our publicly available temporal tagger HeidelTime. Our cross-domain evaluation validates the benefits of domain-sensitive temporal tagging. Furthermore, we make available two new temporally annotated corpora and a new version of HeidelTime, which now distinguishes between four document domain types.</abstract>
<identifier type="citekey">strotgen-gertz-2012-temporal</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/425_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3746</start>
<end>3753</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Temporal Tagging on Different Domains: Challenges, Strategies, and Gold Standards
%A Strötgen, Jannik
%A Gertz, Michael
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F strotgen-gertz-2012-temporal
%X In the last years, temporal tagging has received increasing attention in the area of natural language processing. However, most of the research so far concentrated on processing news documents. Only recently, two temporal annotated corpora of narrative-style documents were developed, and it was shown that a domain shift results in significant challenges for temporal tagging. Thus, a temporal tagger should be aware of the domain associated with documents that are to be processed and apply domain-specific strategies for extracting and normalizing temporal expressions. In this paper, we analyze the characteristics of temporal expressions in different domains. In addition to news- and narrative-style documents, we add two further document types, namely colloquial and scientific documents. After discussing the challenges of temporal tagging on the different domains, we describe some strategies to tackle these challenges and describe their integration into our publicly available temporal tagger HeidelTime. Our cross-domain evaluation validates the benefits of domain-sensitive temporal tagging. Furthermore, we make available two new temporally annotated corpora and a new version of HeidelTime, which now distinguishes between four document domain types.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/425_Paper.pdf
%P 3746-3753
Markdown (Informal)
[Temporal Tagging on Different Domains: Challenges, Strategies, and Gold Standards](http://www.lrec-conf.org/proceedings/lrec2012/pdf/425_Paper.pdf) (Strötgen & Gertz, LREC 2012)
ACL