@inproceedings{basile-etal-2012-developing,
title = "Developing a large semantically annotated corpus",
author = "Basile, Valerio and
Bos, Johan and
Evang, Kilian and
Venhuizen, Noortje",
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/534_Paper.pdf",
pages = "3196--3200",
abstract = "What would be a good method to provide a large collection of semantically annotated texts with formal, deep semantics rather than shallow? We argue that a bootstrapping approach comprising state-of-the-art NLP tools for parsing and semantic interpretation, in combination with a wiki-like interface for collaborative annotation of experts, and a game with a purpose for crowdsourcing, are the starting ingredients for fulfilling this enterprise. The result is a semantic resource that anyone can edit and that integrates various phenomena, including predicate-argument structure, scope, tense, thematic roles, rhetorical relations and presuppositions, into a single semantic formalism: Discourse Representation Theory. Taking texts rather than sentences as the units of annotation results in deep semantic representations that incorporate discourse structure and dependencies. To manage the various (possibly conflicting) annotations provided by experts and non-experts, we introduce a method that stores ``Bits of Wisdom'' in a database as stand-off annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="basile-etal-2012-developing">
<titleInfo>
<title>Developing a large semantically annotated corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johan</namePart>
<namePart type="family">Bos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilian</namePart>
<namePart type="family">Evang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noortje</namePart>
<namePart type="family">Venhuizen</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>What would be a good method to provide a large collection of semantically annotated texts with formal, deep semantics rather than shallow? We argue that a bootstrapping approach comprising state-of-the-art NLP tools for parsing and semantic interpretation, in combination with a wiki-like interface for collaborative annotation of experts, and a game with a purpose for crowdsourcing, are the starting ingredients for fulfilling this enterprise. The result is a semantic resource that anyone can edit and that integrates various phenomena, including predicate-argument structure, scope, tense, thematic roles, rhetorical relations and presuppositions, into a single semantic formalism: Discourse Representation Theory. Taking texts rather than sentences as the units of annotation results in deep semantic representations that incorporate discourse structure and dependencies. To manage the various (possibly conflicting) annotations provided by experts and non-experts, we introduce a method that stores “Bits of Wisdom” in a database as stand-off annotations.</abstract>
<identifier type="citekey">basile-etal-2012-developing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/534_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3196</start>
<end>3200</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing a large semantically annotated corpus
%A Basile, Valerio
%A Bos, Johan
%A Evang, Kilian
%A Venhuizen, Noortje
%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 basile-etal-2012-developing
%X What would be a good method to provide a large collection of semantically annotated texts with formal, deep semantics rather than shallow? We argue that a bootstrapping approach comprising state-of-the-art NLP tools for parsing and semantic interpretation, in combination with a wiki-like interface for collaborative annotation of experts, and a game with a purpose for crowdsourcing, are the starting ingredients for fulfilling this enterprise. The result is a semantic resource that anyone can edit and that integrates various phenomena, including predicate-argument structure, scope, tense, thematic roles, rhetorical relations and presuppositions, into a single semantic formalism: Discourse Representation Theory. Taking texts rather than sentences as the units of annotation results in deep semantic representations that incorporate discourse structure and dependencies. To manage the various (possibly conflicting) annotations provided by experts and non-experts, we introduce a method that stores “Bits of Wisdom” in a database as stand-off annotations.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/534_Paper.pdf
%P 3196-3200
Markdown (Informal)
[Developing a large semantically annotated corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/534_Paper.pdf) (Basile et al., LREC 2012)
ACL
- Valerio Basile, Johan Bos, Kilian Evang, and Noortje Venhuizen. 2012. Developing a large semantically annotated corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3196–3200, Istanbul, Turkey. European Language Resources Association (ELRA).