@inproceedings{sulea-etal-2016-using,
title = "Using Word Embeddings to Translate Named Entities",
author = "{\c{S}}ulea, Octavia-Maria and
Nisioi, Sergiu and
Dinu, Liviu P.",
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/L16-1536",
pages = "3362--3366",
abstract = "In this paper we investigate the usefulness of neural word embeddings in the process of translating Named Entities (NEs) from a resource-rich language to a language low on resources relevant to the task at hand, introducing a novel, yet simple way of obtaining bilingual word vectors. Inspired by observations in (Mikolov et al., 2013b), which show that training their word vector model on comparable corpora yields comparable vector space representations of those corpora, reducing the problem of translating words to finding a rotation matrix, and results in (Zou et al., 2013), which showed that bilingual word embeddings can improve Chinese Named Entity Recognition (NER) and English to Chinese phrase translation, we use the sentence-aligned English-French EuroParl corpora and show that word embeddings extracted from a merged corpus (corpus resulted from the merger of the two aligned corpora) can be used to NE translation. We extrapolate that word embeddings trained on merged parallel corpora are useful in Named Entity Recognition and Translation tasks for resource-poor languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sulea-etal-2016-using">
<titleInfo>
<title>Using Word Embeddings to Translate Named Entities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Octavia-Maria</namePart>
<namePart type="family">Şulea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergiu</namePart>
<namePart type="family">Nisioi</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>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>In this paper we investigate the usefulness of neural word embeddings in the process of translating Named Entities (NEs) from a resource-rich language to a language low on resources relevant to the task at hand, introducing a novel, yet simple way of obtaining bilingual word vectors. Inspired by observations in (Mikolov et al., 2013b), which show that training their word vector model on comparable corpora yields comparable vector space representations of those corpora, reducing the problem of translating words to finding a rotation matrix, and results in (Zou et al., 2013), which showed that bilingual word embeddings can improve Chinese Named Entity Recognition (NER) and English to Chinese phrase translation, we use the sentence-aligned English-French EuroParl corpora and show that word embeddings extracted from a merged corpus (corpus resulted from the merger of the two aligned corpora) can be used to NE translation. We extrapolate that word embeddings trained on merged parallel corpora are useful in Named Entity Recognition and Translation tasks for resource-poor languages.</abstract>
<identifier type="citekey">sulea-etal-2016-using</identifier>
<location>
<url>https://aclanthology.org/L16-1536</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3362</start>
<end>3366</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Word Embeddings to Translate Named Entities
%A Şulea, Octavia-Maria
%A Nisioi, Sergiu
%A Dinu, Liviu P.
%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 sulea-etal-2016-using
%X In this paper we investigate the usefulness of neural word embeddings in the process of translating Named Entities (NEs) from a resource-rich language to a language low on resources relevant to the task at hand, introducing a novel, yet simple way of obtaining bilingual word vectors. Inspired by observations in (Mikolov et al., 2013b), which show that training their word vector model on comparable corpora yields comparable vector space representations of those corpora, reducing the problem of translating words to finding a rotation matrix, and results in (Zou et al., 2013), which showed that bilingual word embeddings can improve Chinese Named Entity Recognition (NER) and English to Chinese phrase translation, we use the sentence-aligned English-French EuroParl corpora and show that word embeddings extracted from a merged corpus (corpus resulted from the merger of the two aligned corpora) can be used to NE translation. We extrapolate that word embeddings trained on merged parallel corpora are useful in Named Entity Recognition and Translation tasks for resource-poor languages.
%U https://aclanthology.org/L16-1536
%P 3362-3366
Markdown (Informal)
[Using Word Embeddings to Translate Named Entities](https://aclanthology.org/L16-1536) (Şulea et al., LREC 2016)
ACL
- Octavia-Maria Şulea, Sergiu Nisioi, and Liviu P. Dinu. 2016. Using Word Embeddings to Translate Named Entities. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3362–3366, Portorož, Slovenia. European Language Resources Association (ELRA).