@inproceedings{kruse-ahmed-2024-tafsirextractor,
title = "{T}afsir{E}xtractor: Text Preprocessing Pipeline preparing Classical {A}rabic Literature for Machine Learning Applications",
author = "Kruse, Carl and
Ahmed, Sajawel",
editor = "Al-Khalifa, Hend and
Darwish, Kareem and
Mubarak, Hamdy and
Ali, Mona and
Elsayed, Tamer",
booktitle = "Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.osact-1.8",
pages = "67--73",
abstract = "In this paper, we present a comprehensive tool of preprocessing Classical Arabic (CA) literature in the field of historical exegetical studies for machine learning (ML) evaluations. Most recent ML models require the training data to be in a specific format (e.g. XML, TEI, CoNLL) to use it afterwards for ML applications such as Named Entity Recognition (NER) or Topic Modeling (TM). We report on how our method works and can be applied by other researchers with similar endeavors. Thereby, the importance of this comprehensive tool of preprocessing is demonstrated, as this novel approach has no predecessors for CA yet. We achieve results that enable the training of current ML models leading to state-of-the art performance for NER and TM on CA literature. We make our tool along its source code and data freely available for the Natural Language Processing (NLP) research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kruse-ahmed-2024-tafsirextractor">
<titleInfo>
<title>TafsirExtractor: Text Preprocessing Pipeline preparing Classical Arabic Literature for Machine Learning Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carl</namePart>
<namePart type="family">Kruse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajawel</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a comprehensive tool of preprocessing Classical Arabic (CA) literature in the field of historical exegetical studies for machine learning (ML) evaluations. Most recent ML models require the training data to be in a specific format (e.g. XML, TEI, CoNLL) to use it afterwards for ML applications such as Named Entity Recognition (NER) or Topic Modeling (TM). We report on how our method works and can be applied by other researchers with similar endeavors. Thereby, the importance of this comprehensive tool of preprocessing is demonstrated, as this novel approach has no predecessors for CA yet. We achieve results that enable the training of current ML models leading to state-of-the art performance for NER and TM on CA literature. We make our tool along its source code and data freely available for the Natural Language Processing (NLP) research community.</abstract>
<identifier type="citekey">kruse-ahmed-2024-tafsirextractor</identifier>
<location>
<url>https://aclanthology.org/2024.osact-1.8</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>67</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TafsirExtractor: Text Preprocessing Pipeline preparing Classical Arabic Literature for Machine Learning Applications
%A Kruse, Carl
%A Ahmed, Sajawel
%Y Al-Khalifa, Hend
%Y Darwish, Kareem
%Y Mubarak, Hamdy
%Y Ali, Mona
%Y Elsayed, Tamer
%S Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F kruse-ahmed-2024-tafsirextractor
%X In this paper, we present a comprehensive tool of preprocessing Classical Arabic (CA) literature in the field of historical exegetical studies for machine learning (ML) evaluations. Most recent ML models require the training data to be in a specific format (e.g. XML, TEI, CoNLL) to use it afterwards for ML applications such as Named Entity Recognition (NER) or Topic Modeling (TM). We report on how our method works and can be applied by other researchers with similar endeavors. Thereby, the importance of this comprehensive tool of preprocessing is demonstrated, as this novel approach has no predecessors for CA yet. We achieve results that enable the training of current ML models leading to state-of-the art performance for NER and TM on CA literature. We make our tool along its source code and data freely available for the Natural Language Processing (NLP) research community.
%U https://aclanthology.org/2024.osact-1.8
%P 67-73
Markdown (Informal)
[TafsirExtractor: Text Preprocessing Pipeline preparing Classical Arabic Literature for Machine Learning Applications](https://aclanthology.org/2024.osact-1.8) (Kruse & Ahmed, OSACT-WS 2024)
ACL