@inproceedings{mendes-etal-2006-combina,
title = "{COMBINA}-{PT}: A Large Corpus-extracted and Hand-checked Lexical Database of {P}ortuguese Multiword Expressions",
author = "Mendes, Am\'alia and
Antunes, Sandra and
Nascimento, Maria Fernanda Bacelar do and
Casteleiro, Jo\~ao Miguel and
Pereira, Lu\'\i sa and
S\'a, Tiago",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}'06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L06-1326/",
abstract = "This paper presents the COMBINA-PT project, a study of corpus-extracted Portuguese Multiword (MW) expressions. The objective of this on-going project is to compile a large lexical database of multiword (MW) units of the Portuguese language, automatically extracted from a balanced 50 million word corpus, and manually validated with the help of lexical association measures. MW expressions considered in the database include named entities and lexical associations with different degrees of cohesion, ranging from frozen groups, which undergo little or no variation, to lexical collocations composed of words that tend to occur together and that constitute syntactic dependencies, although with a low degree of fixedness. This new resource has a two-fold objective: (i) to be an important research tool which supports the development of MW expressions typologies and their lexicographic treatment; (ii) to be of major help in developing and evaluating language processing tools able of dealing with MW expressions."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mendes-etal-2006-combina">
<titleInfo>
<title>COMBINA-PT: A Large Corpus-extracted and Hand-checked Lexical Database of Portuguese Multiword Expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amália</namePart>
<namePart type="family">Mendes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Antunes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Fernanda</namePart>
<namePart type="given">Bacelar</namePart>
<namePart type="given">do</namePart>
<namePart type="family">Nascimento</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="given">Miguel</namePart>
<namePart type="family">Casteleiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luí</namePart>
<namePart type="given">sa</namePart>
<namePart type="family">Pereira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiago</namePart>
<namePart type="family">Sá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the COMBINA-PT project, a study of corpus-extracted Portuguese Multiword (MW) expressions. The objective of this on-going project is to compile a large lexical database of multiword (MW) units of the Portuguese language, automatically extracted from a balanced 50 million word corpus, and manually validated with the help of lexical association measures. MW expressions considered in the database include named entities and lexical associations with different degrees of cohesion, ranging from frozen groups, which undergo little or no variation, to lexical collocations composed of words that tend to occur together and that constitute syntactic dependencies, although with a low degree of fixedness. This new resource has a two-fold objective: (i) to be an important research tool which supports the development of MW expressions typologies and their lexicographic treatment; (ii) to be of major help in developing and evaluating language processing tools able of dealing with MW expressions.</abstract>
<identifier type="citekey">mendes-etal-2006-combina</identifier>
<location>
<url>https://aclanthology.org/L06-1326/</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COMBINA-PT: A Large Corpus-extracted and Hand-checked Lexical Database of Portuguese Multiword Expressions
%A Mendes, Amália
%A Antunes, Sandra
%A Nascimento, Maria Fernanda Bacelar do
%A Casteleiro, João Miguel
%A Pereira, Luí sa
%A Sá, Tiago
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F mendes-etal-2006-combina
%X This paper presents the COMBINA-PT project, a study of corpus-extracted Portuguese Multiword (MW) expressions. The objective of this on-going project is to compile a large lexical database of multiword (MW) units of the Portuguese language, automatically extracted from a balanced 50 million word corpus, and manually validated with the help of lexical association measures. MW expressions considered in the database include named entities and lexical associations with different degrees of cohesion, ranging from frozen groups, which undergo little or no variation, to lexical collocations composed of words that tend to occur together and that constitute syntactic dependencies, although with a low degree of fixedness. This new resource has a two-fold objective: (i) to be an important research tool which supports the development of MW expressions typologies and their lexicographic treatment; (ii) to be of major help in developing and evaluating language processing tools able of dealing with MW expressions.
%U https://aclanthology.org/L06-1326/
Markdown (Informal)
[COMBINA-PT: A Large Corpus-extracted and Hand-checked Lexical Database of Portuguese Multiword Expressions](https://aclanthology.org/L06-1326/) (Mendes et al., LREC 2006)
ACL