@inproceedings{le-sadat-2015-building,
title = "Building a Bilingual {V}ietnamese-{F}rench Named Entity Annotated Corpus through Cross-Linguistic Projection",
author = "Le, Ngoc Tan and
Sadat, Fatiha",
editor = "Lecarpentier, Jean-Marc and
Lucas, Nadine",
booktitle = "Actes de la 22e conf{\'e}rence sur le Traitement Automatique des Langues Naturelles. D{\'e}monstrations",
month = jun,
year = "2015",
address = "Caen, France",
publisher = "ATALA",
url = "https://aclanthology.org/2015.jeptalnrecital-demonstration.6",
pages = "12--13",
abstract = "The creation of high-quality named entity annotated resources is time-consuming and an expensive process. Most of the gold standard corpora are available for English but not for less-resourced languages such as Vietnamese. In Asian languages, this task is remained problematic. This paper focuses on an automatic construction of named entity annotated corpora for Vietnamese-French, a less-resourced pair of languages. We incrementally apply different cross-projection methods using parallel corpora, such as perfect string matching and edit distance similarity. Evaluations on Vietnamese {--}French pair of languages show a good accuracy (F-score of 94.90{\%}) when identifying named entities pairs and building a named entity annotated parallel corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-sadat-2015-building">
<titleInfo>
<title>Building a Bilingual Vietnamese-French Named Entity Annotated Corpus through Cross-Linguistic Projection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ngoc</namePart>
<namePart type="given">Tan</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatiha</namePart>
<namePart type="family">Sadat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2015-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Actes de la 22e conférence sur le Traitement Automatique des Langues Naturelles. Démonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jean-Marc</namePart>
<namePart type="family">Lecarpentier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadine</namePart>
<namePart type="family">Lucas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA</publisher>
<place>
<placeTerm type="text">Caen, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The creation of high-quality named entity annotated resources is time-consuming and an expensive process. Most of the gold standard corpora are available for English but not for less-resourced languages such as Vietnamese. In Asian languages, this task is remained problematic. This paper focuses on an automatic construction of named entity annotated corpora for Vietnamese-French, a less-resourced pair of languages. We incrementally apply different cross-projection methods using parallel corpora, such as perfect string matching and edit distance similarity. Evaluations on Vietnamese –French pair of languages show a good accuracy (F-score of 94.90%) when identifying named entities pairs and building a named entity annotated parallel corpus.</abstract>
<identifier type="citekey">le-sadat-2015-building</identifier>
<location>
<url>https://aclanthology.org/2015.jeptalnrecital-demonstration.6</url>
</location>
<part>
<date>2015-06</date>
<extent unit="page">
<start>12</start>
<end>13</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Bilingual Vietnamese-French Named Entity Annotated Corpus through Cross-Linguistic Projection
%A Le, Ngoc Tan
%A Sadat, Fatiha
%Y Lecarpentier, Jean-Marc
%Y Lucas, Nadine
%S Actes de la 22e conférence sur le Traitement Automatique des Langues Naturelles. Démonstrations
%D 2015
%8 June
%I ATALA
%C Caen, France
%F le-sadat-2015-building
%X The creation of high-quality named entity annotated resources is time-consuming and an expensive process. Most of the gold standard corpora are available for English but not for less-resourced languages such as Vietnamese. In Asian languages, this task is remained problematic. This paper focuses on an automatic construction of named entity annotated corpora for Vietnamese-French, a less-resourced pair of languages. We incrementally apply different cross-projection methods using parallel corpora, such as perfect string matching and edit distance similarity. Evaluations on Vietnamese –French pair of languages show a good accuracy (F-score of 94.90%) when identifying named entities pairs and building a named entity annotated parallel corpus.
%U https://aclanthology.org/2015.jeptalnrecital-demonstration.6
%P 12-13
Markdown (Informal)
[Building a Bilingual Vietnamese-French Named Entity Annotated Corpus through Cross-Linguistic Projection](https://aclanthology.org/2015.jeptalnrecital-demonstration.6) (Le & Sadat, JEP/TALN/RECITAL 2015)
ACL