@inproceedings{moro-etal-2014-annotating,
title = "Annotating the {MASC} Corpus with {B}abel{N}et",
author = "Moro, Andrea and
Navigli, Roberto and
Tucci, Francesco Maria and
Passonneau, Rebecca J.",
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/375_Paper.pdf",
pages = "4214--4219",
abstract = "In this paper we tackle the problem of automatically annotating, with both word senses and named entities, the MASC 3.0 corpus, a large English corpus covering a wide range of genres of written and spoken text. We use BabelNet 2.0, a multilingual semantic network which integrates both lexicographic and encyclopedic knowledge, as our sense/entity inventory together with its semantic structure, to perform the aforementioned annotation task. Word sense annotated corpora have been around for more than twenty years, helping the development of Word Sense Disambiguation algorithms by providing both training and testing grounds. More recently Entity Linking has followed the same path, with the creation of huge resources containing annotated named entities. However, to date, there has been no resource that contains both kinds of annotation. In this paper we present an automatic approach for performing this annotation, together with its output on the MASC corpus. We use this corpus because its goal of integrating different types of annotations goes exactly in our same direction. Our overall aim is to stimulate research on the joint exploitation and disambiguation of word senses and named entities. Finally, we estimate the quality of our annotations using both manually-tagged named entities and word senses, obtaining an accuracy of roughly 70{\%} for both named entities and word sense annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moro-etal-2014-annotating">
<titleInfo>
<title>Annotating the MASC Corpus with BabelNet</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Moro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Tucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Passonneau</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>In this paper we tackle the problem of automatically annotating, with both word senses and named entities, the MASC 3.0 corpus, a large English corpus covering a wide range of genres of written and spoken text. We use BabelNet 2.0, a multilingual semantic network which integrates both lexicographic and encyclopedic knowledge, as our sense/entity inventory together with its semantic structure, to perform the aforementioned annotation task. Word sense annotated corpora have been around for more than twenty years, helping the development of Word Sense Disambiguation algorithms by providing both training and testing grounds. More recently Entity Linking has followed the same path, with the creation of huge resources containing annotated named entities. However, to date, there has been no resource that contains both kinds of annotation. In this paper we present an automatic approach for performing this annotation, together with its output on the MASC corpus. We use this corpus because its goal of integrating different types of annotations goes exactly in our same direction. Our overall aim is to stimulate research on the joint exploitation and disambiguation of word senses and named entities. Finally, we estimate the quality of our annotations using both manually-tagged named entities and word senses, obtaining an accuracy of roughly 70% for both named entities and word sense annotations.</abstract>
<identifier type="citekey">moro-etal-2014-annotating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/375_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>4214</start>
<end>4219</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotating the MASC Corpus with BabelNet
%A Moro, Andrea
%A Navigli, Roberto
%A Tucci, Francesco Maria
%A Passonneau, Rebecca J.
%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 moro-etal-2014-annotating
%X In this paper we tackle the problem of automatically annotating, with both word senses and named entities, the MASC 3.0 corpus, a large English corpus covering a wide range of genres of written and spoken text. We use BabelNet 2.0, a multilingual semantic network which integrates both lexicographic and encyclopedic knowledge, as our sense/entity inventory together with its semantic structure, to perform the aforementioned annotation task. Word sense annotated corpora have been around for more than twenty years, helping the development of Word Sense Disambiguation algorithms by providing both training and testing grounds. More recently Entity Linking has followed the same path, with the creation of huge resources containing annotated named entities. However, to date, there has been no resource that contains both kinds of annotation. In this paper we present an automatic approach for performing this annotation, together with its output on the MASC corpus. We use this corpus because its goal of integrating different types of annotations goes exactly in our same direction. Our overall aim is to stimulate research on the joint exploitation and disambiguation of word senses and named entities. Finally, we estimate the quality of our annotations using both manually-tagged named entities and word senses, obtaining an accuracy of roughly 70% for both named entities and word sense annotations.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/375_Paper.pdf
%P 4214-4219
Markdown (Informal)
[Annotating the MASC Corpus with BabelNet](http://www.lrec-conf.org/proceedings/lrec2014/pdf/375_Paper.pdf) (Moro et al., LREC 2014)
ACL
- Andrea Moro, Roberto Navigli, Francesco Maria Tucci, and Rebecca J. Passonneau. 2014. Annotating the MASC Corpus with BabelNet. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 4214–4219, Reykjavik, Iceland. European Language Resources Association (ELRA).