@inproceedings{de-clercq-etal-2012-evaluating,
title = "Evaluating automatic cross-domain {D}utch semantic role annotation",
author = "De Clercq, Orph{\'e}e and
Hoste, Veronique and
Monachesi, Paola",
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/680_Paper.pdf",
pages = "88--93",
abstract = "In this paper we present the first corpus where one million Dutch words from a variety of text genres have been annotated with semantic roles. 500K have been completely manually verified and used as training material to automatically label another 500K. All data has been annotated following an adapted version of the PropBank guidelines. The corpus's rich text type diversity and the availability of manually verified syntactic dependency structures allowed us to experiment with an existing semantic role labeler for Dutch. In order to test the system's portability across various domains, we experimented with training on individual domains and compared this with training on multiple domains by adding more data. Our results show that training on large data sets is necessary but that including genre-specific training material is also crucial to optimize classification. We observed that a small amount of in-domain training data is already sufficient to improve our semantic role labeler.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-clercq-etal-2012-evaluating">
<titleInfo>
<title>Evaluating automatic cross-domain Dutch semantic role annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Monachesi</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 this paper we present the first corpus where one million Dutch words from a variety of text genres have been annotated with semantic roles. 500K have been completely manually verified and used as training material to automatically label another 500K. All data has been annotated following an adapted version of the PropBank guidelines. The corpus’s rich text type diversity and the availability of manually verified syntactic dependency structures allowed us to experiment with an existing semantic role labeler for Dutch. In order to test the system’s portability across various domains, we experimented with training on individual domains and compared this with training on multiple domains by adding more data. Our results show that training on large data sets is necessary but that including genre-specific training material is also crucial to optimize classification. We observed that a small amount of in-domain training data is already sufficient to improve our semantic role labeler.</abstract>
<identifier type="citekey">de-clercq-etal-2012-evaluating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/680_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>88</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating automatic cross-domain Dutch semantic role annotation
%A De Clercq, Orphée
%A Hoste, Veronique
%A Monachesi, Paola
%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 de-clercq-etal-2012-evaluating
%X In this paper we present the first corpus where one million Dutch words from a variety of text genres have been annotated with semantic roles. 500K have been completely manually verified and used as training material to automatically label another 500K. All data has been annotated following an adapted version of the PropBank guidelines. The corpus’s rich text type diversity and the availability of manually verified syntactic dependency structures allowed us to experiment with an existing semantic role labeler for Dutch. In order to test the system’s portability across various domains, we experimented with training on individual domains and compared this with training on multiple domains by adding more data. Our results show that training on large data sets is necessary but that including genre-specific training material is also crucial to optimize classification. We observed that a small amount of in-domain training data is already sufficient to improve our semantic role labeler.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/680_Paper.pdf
%P 88-93
Markdown (Informal)
[Evaluating automatic cross-domain Dutch semantic role annotation](http://www.lrec-conf.org/proceedings/lrec2012/pdf/680_Paper.pdf) (De Clercq et al., LREC 2012)
ACL