@inproceedings{fisas-etal-2020-collfren,
title = "{C}oll{F}r{E}n: Rich Bilingual {E}nglish{--}{F}rench Collocation Resource",
author = "Fisas, Beatriz and
Espinosa Anke, Luis and
Codina-Filb{\'a}, Joan and
Wanner, Leo",
editor = "Markantonatou, Stella and
McCrae, John and
Mitrovi{\'c}, Jelena and
Tiberius, Carole and
Ramisch, Carlos and
Vaidya, Ashwini and
Osenova, Petya and
Savary, Agata",
booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons",
month = dec,
year = "2020",
address = "online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.mwe-1.1",
pages = "1--12",
abstract = "Collocations in the sense of idiosyncratic lexical co-occurrences of two syntactically bound words traditionally pose a challenge to language learners and many Natural Language Processing (NLP) applications alike. Reliable ground truth (i.e., ideally manually compiled) resources are thus of high value. We present a manually compiled bilingual English{--}French collocation resource with 7,480 collocations in English and 6,733 in French. Each collocation is enriched with information that facilitates its downstream exploitation in NLP tasks such as machine translation, word sense disambiguation, natural language generation, relation classification, and so forth. Our proposed enrichment covers: the semantic category of the collocation (its lexical function), its vector space representation (for each individual word as well as their joint collocation embedding), a subcategorization pattern of both its elements, as well as their corresponding BabelNet id, and finally, indices of their occurrences in large scale reference corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fisas-etal-2020-collfren">
<titleInfo>
<title>CollFrEn: Rich Bilingual English–French Collocation Resource</title>
</titleInfo>
<name type="personal">
<namePart type="given">Beatriz</namePart>
<namePart type="family">Fisas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Espinosa Anke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joan</namePart>
<namePart type="family">Codina-Filbá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stella</namePart>
<namePart type="family">Markantonatou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelena</namePart>
<namePart type="family">Mitrović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carole</namePart>
<namePart type="family">Tiberius</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Ramisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petya</namePart>
<namePart type="family">Osenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Collocations in the sense of idiosyncratic lexical co-occurrences of two syntactically bound words traditionally pose a challenge to language learners and many Natural Language Processing (NLP) applications alike. Reliable ground truth (i.e., ideally manually compiled) resources are thus of high value. We present a manually compiled bilingual English–French collocation resource with 7,480 collocations in English and 6,733 in French. Each collocation is enriched with information that facilitates its downstream exploitation in NLP tasks such as machine translation, word sense disambiguation, natural language generation, relation classification, and so forth. Our proposed enrichment covers: the semantic category of the collocation (its lexical function), its vector space representation (for each individual word as well as their joint collocation embedding), a subcategorization pattern of both its elements, as well as their corresponding BabelNet id, and finally, indices of their occurrences in large scale reference corpora.</abstract>
<identifier type="citekey">fisas-etal-2020-collfren</identifier>
<location>
<url>https://aclanthology.org/2020.mwe-1.1</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CollFrEn: Rich Bilingual English–French Collocation Resource
%A Fisas, Beatriz
%A Espinosa Anke, Luis
%A Codina-Filbá, Joan
%A Wanner, Leo
%Y Markantonatou, Stella
%Y McCrae, John
%Y Mitrović, Jelena
%Y Tiberius, Carole
%Y Ramisch, Carlos
%Y Vaidya, Ashwini
%Y Osenova, Petya
%Y Savary, Agata
%S Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons
%D 2020
%8 December
%I Association for Computational Linguistics
%C online
%F fisas-etal-2020-collfren
%X Collocations in the sense of idiosyncratic lexical co-occurrences of two syntactically bound words traditionally pose a challenge to language learners and many Natural Language Processing (NLP) applications alike. Reliable ground truth (i.e., ideally manually compiled) resources are thus of high value. We present a manually compiled bilingual English–French collocation resource with 7,480 collocations in English and 6,733 in French. Each collocation is enriched with information that facilitates its downstream exploitation in NLP tasks such as machine translation, word sense disambiguation, natural language generation, relation classification, and so forth. Our proposed enrichment covers: the semantic category of the collocation (its lexical function), its vector space representation (for each individual word as well as their joint collocation embedding), a subcategorization pattern of both its elements, as well as their corresponding BabelNet id, and finally, indices of their occurrences in large scale reference corpora.
%U https://aclanthology.org/2020.mwe-1.1
%P 1-12
Markdown (Informal)
[CollFrEn: Rich Bilingual English–French Collocation Resource](https://aclanthology.org/2020.mwe-1.1) (Fisas et al., MWE 2020)
ACL