@inproceedings{pasini-camacho-collados-2020-short,
title = "A Short Survey on Sense-Annotated Corpora",
author = "Pasini, Tommaso and
Camacho-Collados, Jose",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.706",
pages = "5759--5765",
abstract = "Large sense-annotated datasets are increasingly necessary for training deep supervised systems in Word Sense Disambiguation. However, gathering high-quality sense-annotated data for as many instances as possible is a laborious and expensive task. This has led to the proliferation of automatic and semi-automatic methods for overcoming the so-called knowledge-acquisition bottleneck. In this short survey we present an overview of sense-annotated corpora, annotated either manually- or (semi)automatically, that are currently available for different languages and featuring distinct lexical resources as inventory of senses, i.e. WordNet, Wikipedia, BabelNet. Furthermore, we provide the reader with general statistics of each dataset and an analysis of their specific features.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pasini-camacho-collados-2020-short">
<titleInfo>
<title>A Short Survey on Sense-Annotated Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Pasini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-Collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Large sense-annotated datasets are increasingly necessary for training deep supervised systems in Word Sense Disambiguation. However, gathering high-quality sense-annotated data for as many instances as possible is a laborious and expensive task. This has led to the proliferation of automatic and semi-automatic methods for overcoming the so-called knowledge-acquisition bottleneck. In this short survey we present an overview of sense-annotated corpora, annotated either manually- or (semi)automatically, that are currently available for different languages and featuring distinct lexical resources as inventory of senses, i.e. WordNet, Wikipedia, BabelNet. Furthermore, we provide the reader with general statistics of each dataset and an analysis of their specific features.</abstract>
<identifier type="citekey">pasini-camacho-collados-2020-short</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.706</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5759</start>
<end>5765</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Short Survey on Sense-Annotated Corpora
%A Pasini, Tommaso
%A Camacho-Collados, Jose
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F pasini-camacho-collados-2020-short
%X Large sense-annotated datasets are increasingly necessary for training deep supervised systems in Word Sense Disambiguation. However, gathering high-quality sense-annotated data for as many instances as possible is a laborious and expensive task. This has led to the proliferation of automatic and semi-automatic methods for overcoming the so-called knowledge-acquisition bottleneck. In this short survey we present an overview of sense-annotated corpora, annotated either manually- or (semi)automatically, that are currently available for different languages and featuring distinct lexical resources as inventory of senses, i.e. WordNet, Wikipedia, BabelNet. Furthermore, we provide the reader with general statistics of each dataset and an analysis of their specific features.
%U https://aclanthology.org/2020.lrec-1.706
%P 5759-5765
Markdown (Informal)
[A Short Survey on Sense-Annotated Corpora](https://aclanthology.org/2020.lrec-1.706) (Pasini & Camacho-Collados, LREC 2020)
ACL
- Tommaso Pasini and Jose Camacho-Collados. 2020. A Short Survey on Sense-Annotated Corpora. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5759–5765, Marseille, France. European Language Resources Association.