@inproceedings{bassas-kubler-2024-investigating,
title = "Investigating Linguistic Features for {A}rabic {NLI}",
author = {Bassas, Yasmeen and
K{\"u}bler, Sandra},
editor = "Habash, Nizar and
Bouamor, Houda and
Eskander, Ramy and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Abdelali, Ahmed and
Touileb, Samia and
Hamed, Injy and
Onaizan, Yaser and
Alhafni, Bashar and
Antoun, Wissam and
Khalifa, Salam and
Haddad, Hatem and
Zitouni, Imed and
AlKhamissi, Badr and
Almatham, Rawan and
Mrini, Khalil",
booktitle = "Proceedings of The Second Arabic Natural Language Processing Conference",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.arabicnlp-1.17",
doi = "10.18653/v1/2024.arabicnlp-1.17",
pages = "183--192",
abstract = "Native Language Identification (NLI) is concerned with predicting the native language of an author writing in a second language. We investigate NLI for Arabic, with a focus on the types of linguistic information given that Arabic is morphologically rich. We use the Arabic Learner Corpus (ALC) foro training and testing along with a linear SVM. We explore lexical, morpho-syntactic, and syntactic features. Results show that the best single type of information is character n-grams ranging from 2 to 6. Using this model, we achieve an accuracy of 61.84{\%}, thus outperforming previous results (Ionesco, 2015) by 11.74{\%} even though we use an additional 2 L1s. However, when using prefix and suffix sequences, we reach an accuracy of 53.95{\%}, showing that an approximation of unlexicalized features still reaches solid results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bassas-kubler-2024-investigating">
<titleInfo>
<title>Investigating Linguistic Features for Arabic NLI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yasmeen</namePart>
<namePart type="family">Bassas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kübler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Second Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</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">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wissam</namePart>
<namePart type="family">Antoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</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">Badr</namePart>
<namePart type="family">AlKhamissi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Native Language Identification (NLI) is concerned with predicting the native language of an author writing in a second language. We investigate NLI for Arabic, with a focus on the types of linguistic information given that Arabic is morphologically rich. We use the Arabic Learner Corpus (ALC) foro training and testing along with a linear SVM. We explore lexical, morpho-syntactic, and syntactic features. Results show that the best single type of information is character n-grams ranging from 2 to 6. Using this model, we achieve an accuracy of 61.84%, thus outperforming previous results (Ionesco, 2015) by 11.74% even though we use an additional 2 L1s. However, when using prefix and suffix sequences, we reach an accuracy of 53.95%, showing that an approximation of unlexicalized features still reaches solid results.</abstract>
<identifier type="citekey">bassas-kubler-2024-investigating</identifier>
<identifier type="doi">10.18653/v1/2024.arabicnlp-1.17</identifier>
<location>
<url>https://aclanthology.org/2024.arabicnlp-1.17</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>183</start>
<end>192</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Linguistic Features for Arabic NLI
%A Bassas, Yasmeen
%A Kübler, Sandra
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Eskander, Ramy
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Abdelali, Ahmed
%Y Touileb, Samia
%Y Hamed, Injy
%Y Onaizan, Yaser
%Y Alhafni, Bashar
%Y Antoun, Wissam
%Y Khalifa, Salam
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Mrini, Khalil
%S Proceedings of The Second Arabic Natural Language Processing Conference
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F bassas-kubler-2024-investigating
%X Native Language Identification (NLI) is concerned with predicting the native language of an author writing in a second language. We investigate NLI for Arabic, with a focus on the types of linguistic information given that Arabic is morphologically rich. We use the Arabic Learner Corpus (ALC) foro training and testing along with a linear SVM. We explore lexical, morpho-syntactic, and syntactic features. Results show that the best single type of information is character n-grams ranging from 2 to 6. Using this model, we achieve an accuracy of 61.84%, thus outperforming previous results (Ionesco, 2015) by 11.74% even though we use an additional 2 L1s. However, when using prefix and suffix sequences, we reach an accuracy of 53.95%, showing that an approximation of unlexicalized features still reaches solid results.
%R 10.18653/v1/2024.arabicnlp-1.17
%U https://aclanthology.org/2024.arabicnlp-1.17
%U https://doi.org/10.18653/v1/2024.arabicnlp-1.17
%P 183-192
Markdown (Informal)
[Investigating Linguistic Features for Arabic NLI](https://aclanthology.org/2024.arabicnlp-1.17) (Bassas & Kübler, ArabicNLP-WS 2024)
ACL
- Yasmeen Bassas and Sandra Kübler. 2024. Investigating Linguistic Features for Arabic NLI. In Proceedings of The Second Arabic Natural Language Processing Conference, pages 183–192, Bangkok, Thailand. Association for Computational Linguistics.