@inproceedings{simoes-etal-2010-processing,
title = "Processing and Extracting Data from Dicion{\'a}rio Aberto",
author = "Sim{\~o}es, Alberto and
Almeida, Jos{\'e} Jo{\~a}o and
Farinha, Rita",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/90_Paper.pdf",
abstract = "Synonyms dictionaries are useful resources for natural language processing. Unfortunately their availability in digital format is limited, as publishing companies do not release their dictionaries in open digital formats. Dicion{\'a}rio-Aberto (Sim{\~o}es and Farinha, 2010) is an open and free digital synonyms dictionary for the Portuguese language. It is under public domain and in textual digital format, which makes it usable for any task. Synonyms dictionaries are commonly used for the extraction of relations between words, the construction of complex structures like ontologies or thesaurus (comparable to WordNet (Miller et al., 1990)), or just the extraction of lists of words of specific type. This article will present Dicion{\'a}rio-Aberto, discussing how it was created, its main characteristics, the type of information present on it and the formats in which it is available. Follows the description of an API designed specifically to help Dicion{\'a}rio-Aberto processing without the need to tackle with the dictionary format. Finally, we will analyze the results on some data extraction experiments, extracting lists of words from a specific class, and extracting relationships between words.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simoes-etal-2010-processing">
<titleInfo>
<title>Processing and Extracting Data from Dicionário Aberto</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Simões</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">João</namePart>
<namePart type="family">Almeida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rita</namePart>
<namePart type="family">Farinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Synonyms dictionaries are useful resources for natural language processing. Unfortunately their availability in digital format is limited, as publishing companies do not release their dictionaries in open digital formats. Dicionário-Aberto (Simões and Farinha, 2010) is an open and free digital synonyms dictionary for the Portuguese language. It is under public domain and in textual digital format, which makes it usable for any task. Synonyms dictionaries are commonly used for the extraction of relations between words, the construction of complex structures like ontologies or thesaurus (comparable to WordNet (Miller et al., 1990)), or just the extraction of lists of words of specific type. This article will present Dicionário-Aberto, discussing how it was created, its main characteristics, the type of information present on it and the formats in which it is available. Follows the description of an API designed specifically to help Dicionário-Aberto processing without the need to tackle with the dictionary format. Finally, we will analyze the results on some data extraction experiments, extracting lists of words from a specific class, and extracting relationships between words.</abstract>
<identifier type="citekey">simoes-etal-2010-processing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/90_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Processing and Extracting Data from Dicionário Aberto
%A Simões, Alberto
%A Almeida, José João
%A Farinha, Rita
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F simoes-etal-2010-processing
%X Synonyms dictionaries are useful resources for natural language processing. Unfortunately their availability in digital format is limited, as publishing companies do not release their dictionaries in open digital formats. Dicionário-Aberto (Simões and Farinha, 2010) is an open and free digital synonyms dictionary for the Portuguese language. It is under public domain and in textual digital format, which makes it usable for any task. Synonyms dictionaries are commonly used for the extraction of relations between words, the construction of complex structures like ontologies or thesaurus (comparable to WordNet (Miller et al., 1990)), or just the extraction of lists of words of specific type. This article will present Dicionário-Aberto, discussing how it was created, its main characteristics, the type of information present on it and the formats in which it is available. Follows the description of an API designed specifically to help Dicionário-Aberto processing without the need to tackle with the dictionary format. Finally, we will analyze the results on some data extraction experiments, extracting lists of words from a specific class, and extracting relationships between words.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/90_Paper.pdf
Markdown (Informal)
[Processing and Extracting Data from Dicionário Aberto](http://www.lrec-conf.org/proceedings/lrec2010/pdf/90_Paper.pdf) (Simões et al., LREC 2010)
ACL
- Alberto Simões, José João Almeida, and Rita Farinha. 2010. Processing and Extracting Data from Dicionário Aberto. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).