@inproceedings{uban-dinu-2020-automatically,
title = "Automatically Building a Multilingual Lexicon of False {F}riends With No Supervision",
author = "Uban, Ana Sabina and
Dinu, Liviu P.",
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-1.367/",
pages = "3001--3007",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "Cognate words, defined as words in different languages which derive from a common etymon, can be useful for language learners, who can leverage the orthographical similarity of cognates to more easily understand a text in a foreign language. Deceptive cognates, or false friends, do not share the same meaning anymore; these can be instead deceiving and detrimental for language acquisition or text understanding in a foreign language. We use an automatic method of detecting false friends from a set of cognates, in a fully unsupervised fashion, based on cross-lingual word embeddings. We implement our method for English and five Romance languages, including a low-resource language (Romanian), and evaluate it against two different gold standards. The method can be extended easily to any language pair, requiring only large monolingual corpora for the involved languages and a small bilingual dictionary for the pair. We additionally propose a measure of {\textquotedblleft}falseness{\textquotedblright} of a false friends pair. We publish freely the database of false friends in the six languages, along with the falseness scores for each cognate pair. The resource is the largest of the kind that we are aware of, both in terms of languages covered and number of word pairs."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uban-dinu-2020-automatically">
<titleInfo>
<title>Automatically Building a Multilingual Lexicon of False Friends With No Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="given">Sabina</namePart>
<namePart type="family">Uban</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liviu</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Dinu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">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>Cognate words, defined as words in different languages which derive from a common etymon, can be useful for language learners, who can leverage the orthographical similarity of cognates to more easily understand a text in a foreign language. Deceptive cognates, or false friends, do not share the same meaning anymore; these can be instead deceiving and detrimental for language acquisition or text understanding in a foreign language. We use an automatic method of detecting false friends from a set of cognates, in a fully unsupervised fashion, based on cross-lingual word embeddings. We implement our method for English and five Romance languages, including a low-resource language (Romanian), and evaluate it against two different gold standards. The method can be extended easily to any language pair, requiring only large monolingual corpora for the involved languages and a small bilingual dictionary for the pair. We additionally propose a measure of “falseness” of a false friends pair. We publish freely the database of false friends in the six languages, along with the falseness scores for each cognate pair. The resource is the largest of the kind that we are aware of, both in terms of languages covered and number of word pairs.</abstract>
<identifier type="citekey">uban-dinu-2020-automatically</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.367/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3001</start>
<end>3007</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatically Building a Multilingual Lexicon of False Friends With No Supervision
%A Uban, Ana Sabina
%A Dinu, Liviu P.
%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 eng
%F uban-dinu-2020-automatically
%X Cognate words, defined as words in different languages which derive from a common etymon, can be useful for language learners, who can leverage the orthographical similarity of cognates to more easily understand a text in a foreign language. Deceptive cognates, or false friends, do not share the same meaning anymore; these can be instead deceiving and detrimental for language acquisition or text understanding in a foreign language. We use an automatic method of detecting false friends from a set of cognates, in a fully unsupervised fashion, based on cross-lingual word embeddings. We implement our method for English and five Romance languages, including a low-resource language (Romanian), and evaluate it against two different gold standards. The method can be extended easily to any language pair, requiring only large monolingual corpora for the involved languages and a small bilingual dictionary for the pair. We additionally propose a measure of “falseness” of a false friends pair. We publish freely the database of false friends in the six languages, along with the falseness scores for each cognate pair. The resource is the largest of the kind that we are aware of, both in terms of languages covered and number of word pairs.
%U https://aclanthology.org/2020.lrec-1.367/
%P 3001-3007
Markdown (Informal)
[Automatically Building a Multilingual Lexicon of False Friends With No Supervision](https://aclanthology.org/2020.lrec-1.367/) (Uban & Dinu, LREC 2020)
ACL