@inproceedings{hadj-mohamed-etal-2023-alphamwe,
title = "{A}lpha{MWE}-{A}rabic: {A}rabic Edition of Multilingual Parallel Corpora with Multiword Expression Annotations",
author = "Hadj Mohamed, Najet and
Rassem, Malak and
Han, Lifeng and
Nenadic, Goran",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ranlp-1.50",
pages = "448--457",
abstract = "Multiword Expressions (MWEs) have been a bottleneck for Natural Language Understanding (NLU) and Natural Language Generation (NLG) tasks due to their idiomaticity, ambiguity, and non-compositionality. Bilingual parallel corpora introducing MWE annotations are very scarce which set another challenge for current Natural Language Processing (NLP) systems, especially in a multilingual setting. This work presents AlphaMWE-Arabic, an Arabic edition of the AlphaMWE parallel corpus with MWE annotations. We introduce how we created this corpus including machine translation (MT), post-editing, and annotations for both standard and dialectal varieties, i.e. Tunisian and Egyptian Arabic. We analyse the MT errors when they meet MWEs-related content, both quantitatively using the human-in-the-loop metric HOPE and qualitatively. We report the current state-of-the-art MT systems are far from reaching human parity performances. We expect our bilingual English-Arabic corpus will be an asset for multilingual research on MWEs such as translation and localisation, as well as for monolingual settings including the study of Arabic-specific lexicography and phrasal verbs on MWEs. Our corpus and experimental data are available at \url{https://github.com/aaronlifenghan/AlphaMWE}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hadj-mohamed-etal-2023-alphamwe">
<titleInfo>
<title>AlphaMWE-Arabic: Arabic Edition of Multilingual Parallel Corpora with Multiword Expression Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Najet</namePart>
<namePart type="family">Hadj Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malak</namePart>
<namePart type="family">Rassem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Nenadic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing</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., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multiword Expressions (MWEs) have been a bottleneck for Natural Language Understanding (NLU) and Natural Language Generation (NLG) tasks due to their idiomaticity, ambiguity, and non-compositionality. Bilingual parallel corpora introducing MWE annotations are very scarce which set another challenge for current Natural Language Processing (NLP) systems, especially in a multilingual setting. This work presents AlphaMWE-Arabic, an Arabic edition of the AlphaMWE parallel corpus with MWE annotations. We introduce how we created this corpus including machine translation (MT), post-editing, and annotations for both standard and dialectal varieties, i.e. Tunisian and Egyptian Arabic. We analyse the MT errors when they meet MWEs-related content, both quantitatively using the human-in-the-loop metric HOPE and qualitatively. We report the current state-of-the-art MT systems are far from reaching human parity performances. We expect our bilingual English-Arabic corpus will be an asset for multilingual research on MWEs such as translation and localisation, as well as for monolingual settings including the study of Arabic-specific lexicography and phrasal verbs on MWEs. Our corpus and experimental data are available at https://github.com/aaronlifenghan/AlphaMWE.</abstract>
<identifier type="citekey">hadj-mohamed-etal-2023-alphamwe</identifier>
<location>
<url>https://aclanthology.org/2023.ranlp-1.50</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>448</start>
<end>457</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AlphaMWE-Arabic: Arabic Edition of Multilingual Parallel Corpora with Multiword Expression Annotations
%A Hadj Mohamed, Najet
%A Rassem, Malak
%A Han, Lifeng
%A Nenadic, Goran
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F hadj-mohamed-etal-2023-alphamwe
%X Multiword Expressions (MWEs) have been a bottleneck for Natural Language Understanding (NLU) and Natural Language Generation (NLG) tasks due to their idiomaticity, ambiguity, and non-compositionality. Bilingual parallel corpora introducing MWE annotations are very scarce which set another challenge for current Natural Language Processing (NLP) systems, especially in a multilingual setting. This work presents AlphaMWE-Arabic, an Arabic edition of the AlphaMWE parallel corpus with MWE annotations. We introduce how we created this corpus including machine translation (MT), post-editing, and annotations for both standard and dialectal varieties, i.e. Tunisian and Egyptian Arabic. We analyse the MT errors when they meet MWEs-related content, both quantitatively using the human-in-the-loop metric HOPE and qualitatively. We report the current state-of-the-art MT systems are far from reaching human parity performances. We expect our bilingual English-Arabic corpus will be an asset for multilingual research on MWEs such as translation and localisation, as well as for monolingual settings including the study of Arabic-specific lexicography and phrasal verbs on MWEs. Our corpus and experimental data are available at https://github.com/aaronlifenghan/AlphaMWE.
%U https://aclanthology.org/2023.ranlp-1.50
%P 448-457
Markdown (Informal)
[AlphaMWE-Arabic: Arabic Edition of Multilingual Parallel Corpora with Multiword Expression Annotations](https://aclanthology.org/2023.ranlp-1.50) (Hadj Mohamed et al., RANLP 2023)
ACL