@inproceedings{lachraf-etal-2019-arbengvec,
title = "{A}rb{E}ng{V}ec : {A}rabic-{E}nglish Cross-Lingual Word Embedding Model",
author = "Lachraf, Raki and
Nagoudi, El Moatez Billah and
Ayachi, Youcef and
Abdelali, Ahmed and
Schwab, Didier",
editor = "El-Hajj, Wassim and
Belguith, Lamia Hadrich and
Bougares, Fethi and
Magdy, Walid and
Zitouni, Imed and
Tomeh, Nadi and
El-Haj, Mahmoud and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fourth Arabic Natural Language Processing Workshop",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4605",
doi = "10.18653/v1/W19-4605",
pages = "40--48",
abstract = "Word Embeddings (WE) are getting increasingly popular and widely applied in many Natural Language Processing (NLP) applications due to their effectiveness in capturing semantic properties of words; Machine Translation (MT), Information Retrieval (IR) and Information Extraction (IE) are among such areas. In this paper, we propose an open source ArbEngVec which provides several Arabic-English cross-lingual word embedding models. To train our bilingual models, we use a large dataset with more than 93 million pairs of Arabic-English parallel sentences. In addition, we perform both extrinsic and intrinsic evaluations for the different word embedding model variants. The extrinsic evaluation assesses the performance of models on the cross-language Semantic Textual Similarity (STS), while the intrinsic evaluation is based on the Word Translation (WT) task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lachraf-etal-2019-arbengvec">
<titleInfo>
<title>ArbEngVec : Arabic-English Cross-Lingual Word Embedding Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raki</namePart>
<namePart type="family">Lachraf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">El</namePart>
<namePart type="given">Moatez</namePart>
<namePart type="given">Billah</namePart>
<namePart type="family">Nagoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youcef</namePart>
<namePart type="family">Ayachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Didier</namePart>
<namePart type="family">Schwab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wassim</namePart>
<namePart type="family">El-Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="given">Hadrich</namePart>
<namePart type="family">Belguith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word Embeddings (WE) are getting increasingly popular and widely applied in many Natural Language Processing (NLP) applications due to their effectiveness in capturing semantic properties of words; Machine Translation (MT), Information Retrieval (IR) and Information Extraction (IE) are among such areas. In this paper, we propose an open source ArbEngVec which provides several Arabic-English cross-lingual word embedding models. To train our bilingual models, we use a large dataset with more than 93 million pairs of Arabic-English parallel sentences. In addition, we perform both extrinsic and intrinsic evaluations for the different word embedding model variants. The extrinsic evaluation assesses the performance of models on the cross-language Semantic Textual Similarity (STS), while the intrinsic evaluation is based on the Word Translation (WT) task.</abstract>
<identifier type="citekey">lachraf-etal-2019-arbengvec</identifier>
<identifier type="doi">10.18653/v1/W19-4605</identifier>
<location>
<url>https://aclanthology.org/W19-4605</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>40</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArbEngVec : Arabic-English Cross-Lingual Word Embedding Model
%A Lachraf, Raki
%A Nagoudi, El Moatez Billah
%A Ayachi, Youcef
%A Abdelali, Ahmed
%A Schwab, Didier
%Y El-Hajj, Wassim
%Y Belguith, Lamia Hadrich
%Y Bougares, Fethi
%Y Magdy, Walid
%Y Zitouni, Imed
%Y Tomeh, Nadi
%Y El-Haj, Mahmoud
%Y Zaghouani, Wajdi
%S Proceedings of the Fourth Arabic Natural Language Processing Workshop
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F lachraf-etal-2019-arbengvec
%X Word Embeddings (WE) are getting increasingly popular and widely applied in many Natural Language Processing (NLP) applications due to their effectiveness in capturing semantic properties of words; Machine Translation (MT), Information Retrieval (IR) and Information Extraction (IE) are among such areas. In this paper, we propose an open source ArbEngVec which provides several Arabic-English cross-lingual word embedding models. To train our bilingual models, we use a large dataset with more than 93 million pairs of Arabic-English parallel sentences. In addition, we perform both extrinsic and intrinsic evaluations for the different word embedding model variants. The extrinsic evaluation assesses the performance of models on the cross-language Semantic Textual Similarity (STS), while the intrinsic evaluation is based on the Word Translation (WT) task.
%R 10.18653/v1/W19-4605
%U https://aclanthology.org/W19-4605
%U https://doi.org/10.18653/v1/W19-4605
%P 40-48
Markdown (Informal)
[ArbEngVec : Arabic-English Cross-Lingual Word Embedding Model](https://aclanthology.org/W19-4605) (Lachraf et al., WANLP 2019)
ACL
- Raki Lachraf, El Moatez Billah Nagoudi, Youcef Ayachi, Ahmed Abdelali, and Didier Schwab. 2019. ArbEngVec : Arabic-English Cross-Lingual Word Embedding Model. In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 40–48, Florence, Italy. Association for Computational Linguistics.