@inproceedings{castro-etal-2018-high,
title = "A High Coverage Method for Automatic False {F}riends Detection for {S}panish and {P}ortuguese",
author = "Castro, Santiago and
Bonanata, Jairo and
Ros{\'a}, Aiala",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shervin and
Ali, Ahmed},
booktitle = "Proceedings of the Fifth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial 2018)",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3903",
pages = "29--36",
abstract = "False friends are words in two languages that look or sound similar, but have different meanings. They are a common source of confusion among language learners. Methods to detect them automatically do exist, however they make use of large aligned bilingual corpora, which are hard to find and expensive to build, or encounter problems dealing with infrequent words. In this work we propose a high coverage method that uses word vector representations to build a false friends classifier for any pair of languages, which we apply to the particular case of Spanish and Portuguese. The required resources are a large corpus for each language and a small bilingual lexicon for the pair.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="castro-etal-2018-high">
<titleInfo>
<title>A High Coverage Method for Automatic False Friends Detection for Spanish and Portuguese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Castro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jairo</namePart>
<namePart type="family">Bonanata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>False friends are words in two languages that look or sound similar, but have different meanings. They are a common source of confusion among language learners. Methods to detect them automatically do exist, however they make use of large aligned bilingual corpora, which are hard to find and expensive to build, or encounter problems dealing with infrequent words. In this work we propose a high coverage method that uses word vector representations to build a false friends classifier for any pair of languages, which we apply to the particular case of Spanish and Portuguese. The required resources are a large corpus for each language and a small bilingual lexicon for the pair.</abstract>
<identifier type="citekey">castro-etal-2018-high</identifier>
<location>
<url>https://aclanthology.org/W18-3903</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>29</start>
<end>36</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A High Coverage Method for Automatic False Friends Detection for Spanish and Portuguese
%A Castro, Santiago
%A Bonanata, Jairo
%A Rosá, Aiala
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shervin
%Y Ali, Ahmed
%S Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F castro-etal-2018-high
%X False friends are words in two languages that look or sound similar, but have different meanings. They are a common source of confusion among language learners. Methods to detect them automatically do exist, however they make use of large aligned bilingual corpora, which are hard to find and expensive to build, or encounter problems dealing with infrequent words. In this work we propose a high coverage method that uses word vector representations to build a false friends classifier for any pair of languages, which we apply to the particular case of Spanish and Portuguese. The required resources are a large corpus for each language and a small bilingual lexicon for the pair.
%U https://aclanthology.org/W18-3903
%P 29-36
Markdown (Informal)
[A High Coverage Method for Automatic False Friends Detection for Spanish and Portuguese](https://aclanthology.org/W18-3903) (Castro et al., VarDial 2018)
ACL