@inproceedings{nguer-etal-2020-sencorpus,
title = "{SENCORPUS}: A {F}rench-{W}olof Parallel Corpus",
author = "Nguer, Elhadji Mamadou and
Lo, Alla and
Dione, Cheikh M. Bamba and
Ba, Sileye O. and
Lo, Moussa",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.341",
pages = "2803--2811",
abstract = "In this paper, we report efforts towards the acquisition and construction of a bilingual parallel corpus between French and Wolof, a Niger-Congo language belonging to the Northern branch of the Atlantic group. The corpus is constructed as part of the SYSNET3LOc project. It currently contains about 70,000 French-Wolof parallel sentences drawn on various sources from different domains. The paper discusses the data collection procedure, conversion, and alignment of the corpus as well as it{'}s application as training data for neural machine translation. In fact, using this corpus, we were able to create word embedding models for Wolof with relatively good results. Currently, the corpus is being used to develop a neural machine translation model to translate French sentences into Wolof.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguer-etal-2020-sencorpus">
<titleInfo>
<title>SENCORPUS: A French-Wolof Parallel Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elhadji</namePart>
<namePart type="given">Mamadou</namePart>
<namePart type="family">Nguer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alla</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheikh</namePart>
<namePart type="given">M</namePart>
<namePart type="given">Bamba</namePart>
<namePart type="family">Dione</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sileye</namePart>
<namePart type="given">O</namePart>
<namePart type="family">Ba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moussa</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<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>In this paper, we report efforts towards the acquisition and construction of a bilingual parallel corpus between French and Wolof, a Niger-Congo language belonging to the Northern branch of the Atlantic group. The corpus is constructed as part of the SYSNET3LOc project. It currently contains about 70,000 French-Wolof parallel sentences drawn on various sources from different domains. The paper discusses the data collection procedure, conversion, and alignment of the corpus as well as it’s application as training data for neural machine translation. In fact, using this corpus, we were able to create word embedding models for Wolof with relatively good results. Currently, the corpus is being used to develop a neural machine translation model to translate French sentences into Wolof.</abstract>
<identifier type="citekey">nguer-etal-2020-sencorpus</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.341</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>2803</start>
<end>2811</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SENCORPUS: A French-Wolof Parallel Corpus
%A Nguer, Elhadji Mamadou
%A Lo, Alla
%A Dione, Cheikh M. Bamba
%A Ba, Sileye O.
%A Lo, Moussa
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F nguer-etal-2020-sencorpus
%X In this paper, we report efforts towards the acquisition and construction of a bilingual parallel corpus between French and Wolof, a Niger-Congo language belonging to the Northern branch of the Atlantic group. The corpus is constructed as part of the SYSNET3LOc project. It currently contains about 70,000 French-Wolof parallel sentences drawn on various sources from different domains. The paper discusses the data collection procedure, conversion, and alignment of the corpus as well as it’s application as training data for neural machine translation. In fact, using this corpus, we were able to create word embedding models for Wolof with relatively good results. Currently, the corpus is being used to develop a neural machine translation model to translate French sentences into Wolof.
%U https://aclanthology.org/2020.lrec-1.341
%P 2803-2811
Markdown (Informal)
[SENCORPUS: A French-Wolof Parallel Corpus](https://aclanthology.org/2020.lrec-1.341) (Nguer et al., LREC 2020)
ACL
- Elhadji Mamadou Nguer, Alla Lo, Cheikh M. Bamba Dione, Sileye O. Ba, and Moussa Lo. 2020. SENCORPUS: A French-Wolof Parallel Corpus. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 2803–2811, Marseille, France. European Language Resources Association.