@inproceedings{karout-etal-2026-arabic,
title = "{A}rabic Citation Parsing using Part of Speech and Named Entity Recognition",
author = "Karout, Youssef and
Hammoud, Hadi and
Zaraket, Fadi",
booktitle = "Proceedings of the 2nd Workshop on {NLP} for Languages Using {A}rabic Script",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.abjadnlp-1.33/",
pages = "245--252",
abstract = "This paper introduces an industry level citation element extractor from Arabic text. Citation element extraction enables editorial task automation for publishing houses, creation of citation networks, and automatic citation analytics for impact analysis firms. Citation library tools help users manage their citations. However, for Arabic, these tools lack basic support to identify and extract citation elements. Consequently, researchers, editors and reviewers manually manage Arabic citations tasks. We present a novel Arabic citation element dataset, use it to train a citation element extraction model, and use named entity recognition, morphological analysis, and keyword detection to improve the results for practical use. The paper reports industry ready performance with F1 scores ranging between .80 and .95 for interesting citation elements."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karout-etal-2026-arabic">
<titleInfo>
<title>Arabic Citation Parsing using Part of Speech and Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Youssef</namePart>
<namePart type="family">Karout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hadi</namePart>
<namePart type="family">Hammoud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fadi</namePart>
<namePart type="family">Zaraket</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces an industry level citation element extractor from Arabic text. Citation element extraction enables editorial task automation for publishing houses, creation of citation networks, and automatic citation analytics for impact analysis firms. Citation library tools help users manage their citations. However, for Arabic, these tools lack basic support to identify and extract citation elements. Consequently, researchers, editors and reviewers manually manage Arabic citations tasks. We present a novel Arabic citation element dataset, use it to train a citation element extraction model, and use named entity recognition, morphological analysis, and keyword detection to improve the results for practical use. The paper reports industry ready performance with F1 scores ranging between .80 and .95 for interesting citation elements.</abstract>
<identifier type="citekey">karout-etal-2026-arabic</identifier>
<location>
<url>https://aclanthology.org/2026.abjadnlp-1.33/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>245</start>
<end>252</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Citation Parsing using Part of Speech and Named Entity Recognition
%A Karout, Youssef
%A Hammoud, Hadi
%A Zaraket, Fadi
%S Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F karout-etal-2026-arabic
%X This paper introduces an industry level citation element extractor from Arabic text. Citation element extraction enables editorial task automation for publishing houses, creation of citation networks, and automatic citation analytics for impact analysis firms. Citation library tools help users manage their citations. However, for Arabic, these tools lack basic support to identify and extract citation elements. Consequently, researchers, editors and reviewers manually manage Arabic citations tasks. We present a novel Arabic citation element dataset, use it to train a citation element extraction model, and use named entity recognition, morphological analysis, and keyword detection to improve the results for practical use. The paper reports industry ready performance with F1 scores ranging between .80 and .95 for interesting citation elements.
%U https://aclanthology.org/2026.abjadnlp-1.33/
%P 245-252
Markdown (Informal)
[Arabic Citation Parsing using Part of Speech and Named Entity Recognition](https://aclanthology.org/2026.abjadnlp-1.33/) (Karout et al., AbjadNLP 2026)
ACL