@inproceedings{almansor-al-ani-2017-translating,
title = "Translating Dialectal {A}rabic as Low Resource Language using Word Embedding",
author = "Almansor, Ebtesam H and
Al-Ani, Ahmed",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference Recent Advances in Natural Language Processing, {RANLP} 2017",
month = sep,
year = "2017",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://doi.org/10.26615/978-954-452-049-6_008",
doi = "10.26615/978-954-452-049-6_008",
pages = "52--57",
abstract = "A number of machine translation methods have been proposed in recent years to deal with the increasingly important problem of automatic translation between texts of different languages or languages and their dialects. These methods have produced promising results when applied to some of the widely studied languages. Existing translation methods are mainly implemented using rule-based and static machine translation approaches. Rule based approaches utilize language translation rules that can either be constructed by an expert, which is quite difficult when dealing with dialects, or rely on rule construction algorithms, which require very large parallel datasets. Statistical approaches also require large parallel datasets to build the translation models. However, large parallel datasets do not exist for languages with low resources, such as the Arabic language and its dialects. In this paper we propose an algorithm that attempts to overcome this limitation, and apply it to translate the Egyptian dialect (EGY) to Modern Standard Arabic (MSA). Monolingual corpus was collected for both MSA and EGY and a relatively small parallel language pair set was built to train the models. The proposed method utilizes Word embedding as it requires monolingual data rather than parallel corpus. Both Continuous Bag of Words and Skip-gram were used to build word vectors. The proposed method was validated on four different datasets using a four-fold cross validation approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almansor-al-ani-2017-translating">
<titleInfo>
<title>Translating Dialectal Arabic as Low Resource Language using Word Embedding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ebtesam</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Almansor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Al-Ani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A number of machine translation methods have been proposed in recent years to deal with the increasingly important problem of automatic translation between texts of different languages or languages and their dialects. These methods have produced promising results when applied to some of the widely studied languages. Existing translation methods are mainly implemented using rule-based and static machine translation approaches. Rule based approaches utilize language translation rules that can either be constructed by an expert, which is quite difficult when dealing with dialects, or rely on rule construction algorithms, which require very large parallel datasets. Statistical approaches also require large parallel datasets to build the translation models. However, large parallel datasets do not exist for languages with low resources, such as the Arabic language and its dialects. In this paper we propose an algorithm that attempts to overcome this limitation, and apply it to translate the Egyptian dialect (EGY) to Modern Standard Arabic (MSA). Monolingual corpus was collected for both MSA and EGY and a relatively small parallel language pair set was built to train the models. The proposed method utilizes Word embedding as it requires monolingual data rather than parallel corpus. Both Continuous Bag of Words and Skip-gram were used to build word vectors. The proposed method was validated on four different datasets using a four-fold cross validation approach.</abstract>
<identifier type="citekey">almansor-al-ani-2017-translating</identifier>
<identifier type="doi">10.26615/978-954-452-049-6_008</identifier>
<part>
<date>2017-09</date>
<extent unit="page">
<start>52</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translating Dialectal Arabic as Low Resource Language using Word Embedding
%A Almansor, Ebtesam H.
%A Al-Ani, Ahmed
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
%D 2017
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F almansor-al-ani-2017-translating
%X A number of machine translation methods have been proposed in recent years to deal with the increasingly important problem of automatic translation between texts of different languages or languages and their dialects. These methods have produced promising results when applied to some of the widely studied languages. Existing translation methods are mainly implemented using rule-based and static machine translation approaches. Rule based approaches utilize language translation rules that can either be constructed by an expert, which is quite difficult when dealing with dialects, or rely on rule construction algorithms, which require very large parallel datasets. Statistical approaches also require large parallel datasets to build the translation models. However, large parallel datasets do not exist for languages with low resources, such as the Arabic language and its dialects. In this paper we propose an algorithm that attempts to overcome this limitation, and apply it to translate the Egyptian dialect (EGY) to Modern Standard Arabic (MSA). Monolingual corpus was collected for both MSA and EGY and a relatively small parallel language pair set was built to train the models. The proposed method utilizes Word embedding as it requires monolingual data rather than parallel corpus. Both Continuous Bag of Words and Skip-gram were used to build word vectors. The proposed method was validated on four different datasets using a four-fold cross validation approach.
%R 10.26615/978-954-452-049-6_008
%U https://doi.org/10.26615/978-954-452-049-6_008
%P 52-57
Markdown (Informal)
[Translating Dialectal Arabic as Low Resource Language using Word Embedding](https://doi.org/10.26615/978-954-452-049-6_008) (Almansor & Al-Ani, RANLP 2017)
ACL