@inproceedings{jacquet-etal-2016-cross,
title = "Cross-lingual Linking of Multi-word Entities and their corresponding Acronyms",
author = {Jacquet, Guillaume and
Ehrmann, Maud and
Steinberger, Ralf and
V{\"a}yrynen, Jaakko},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1084",
pages = "528--535",
abstract = "This paper reports on an approach and experiments to automatically build a cross-lingual multi-word entity resource. Starting from a collection of millions of acronym/expansion pairs for 22 languages where expansion variants were grouped into monolingual clusters, we experiment with several aggregation strategies to link these clusters across languages. Aggregation strategies make use of string similarity distances and translation probabilities and they are based on vector space and graph representations. The accuracy of the approach is evaluated against Wikipedia{'}s redirection and cross-lingual linking tables. The resulting multi-word entity resource contains 64,000 multi-word entities with unique identifiers and their 600,000 multilingual lexical variants. We intend to make this new resource publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jacquet-etal-2016-cross">
<titleInfo>
<title>Cross-lingual Linking of Multi-word Entities and their corresponding Acronyms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Jacquet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maud</namePart>
<namePart type="family">Ehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralf</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaakko</namePart>
<namePart type="family">Väyrynen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper reports on an approach and experiments to automatically build a cross-lingual multi-word entity resource. Starting from a collection of millions of acronym/expansion pairs for 22 languages where expansion variants were grouped into monolingual clusters, we experiment with several aggregation strategies to link these clusters across languages. Aggregation strategies make use of string similarity distances and translation probabilities and they are based on vector space and graph representations. The accuracy of the approach is evaluated against Wikipedia’s redirection and cross-lingual linking tables. The resulting multi-word entity resource contains 64,000 multi-word entities with unique identifiers and their 600,000 multilingual lexical variants. We intend to make this new resource publicly available.</abstract>
<identifier type="citekey">jacquet-etal-2016-cross</identifier>
<location>
<url>https://aclanthology.org/L16-1084</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>528</start>
<end>535</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-lingual Linking of Multi-word Entities and their corresponding Acronyms
%A Jacquet, Guillaume
%A Ehrmann, Maud
%A Steinberger, Ralf
%A Väyrynen, Jaakko
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F jacquet-etal-2016-cross
%X This paper reports on an approach and experiments to automatically build a cross-lingual multi-word entity resource. Starting from a collection of millions of acronym/expansion pairs for 22 languages where expansion variants were grouped into monolingual clusters, we experiment with several aggregation strategies to link these clusters across languages. Aggregation strategies make use of string similarity distances and translation probabilities and they are based on vector space and graph representations. The accuracy of the approach is evaluated against Wikipedia’s redirection and cross-lingual linking tables. The resulting multi-word entity resource contains 64,000 multi-word entities with unique identifiers and their 600,000 multilingual lexical variants. We intend to make this new resource publicly available.
%U https://aclanthology.org/L16-1084
%P 528-535
Markdown (Informal)
[Cross-lingual Linking of Multi-word Entities and their corresponding Acronyms](https://aclanthology.org/L16-1084) (Jacquet et al., LREC 2016)
ACL