@inproceedings{alshammeri-etal-2021-classifying,
title = "Classifying Verses of the {Q}uran using Doc2vec",
author = "Alshammeri, Menwa and
Atwell, Eric and
Alsalka, Mohammad",
editor = "Bandyopadhyay, Sivaji and
Devi, Sobha Lalitha and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2021",
address = "National Institute of Technology Silchar, Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-main.34",
pages = "284--288",
abstract = "The Quran, as a significant religious text, bears important spiritual and linguistic values. Understanding the text and inferring the underlying meanings entails semantic similarity analysis. We classified the verses of the Quran into 15 pre-defined categories or concepts, based on the Qurany corpus, using Doc2Vec and Logistic Regression. Our classifier scored 70{\%} accuracy, and 60{\%} F1-score using the distributed bag-of-words architecture. We then measured how similar the documents within the same category are to each other semantically and use this information to evaluate our model. We calculated the mean difference and average similarity values for each category to indicate how well our model describes that category.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alshammeri-etal-2021-classifying">
<titleInfo>
<title>Classifying Verses of the Quran using Doc2vec</title>
</titleInfo>
<name type="personal">
<namePart type="given">Menwa</namePart>
<namePart type="family">Alshammeri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Atwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Alsalka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="given">Lalitha</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">National Institute of Technology Silchar, Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Quran, as a significant religious text, bears important spiritual and linguistic values. Understanding the text and inferring the underlying meanings entails semantic similarity analysis. We classified the verses of the Quran into 15 pre-defined categories or concepts, based on the Qurany corpus, using Doc2Vec and Logistic Regression. Our classifier scored 70% accuracy, and 60% F1-score using the distributed bag-of-words architecture. We then measured how similar the documents within the same category are to each other semantically and use this information to evaluate our model. We calculated the mean difference and average similarity values for each category to indicate how well our model describes that category.</abstract>
<identifier type="citekey">alshammeri-etal-2021-classifying</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.34</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>284</start>
<end>288</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Classifying Verses of the Quran using Doc2vec
%A Alshammeri, Menwa
%A Atwell, Eric
%A Alsalka, Mohammad
%Y Bandyopadhyay, Sivaji
%Y Devi, Sobha Lalitha
%Y Bhattacharyya, Pushpak
%S Proceedings of the 18th International Conference on Natural Language Processing (ICON)
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C National Institute of Technology Silchar, Silchar, India
%F alshammeri-etal-2021-classifying
%X The Quran, as a significant religious text, bears important spiritual and linguistic values. Understanding the text and inferring the underlying meanings entails semantic similarity analysis. We classified the verses of the Quran into 15 pre-defined categories or concepts, based on the Qurany corpus, using Doc2Vec and Logistic Regression. Our classifier scored 70% accuracy, and 60% F1-score using the distributed bag-of-words architecture. We then measured how similar the documents within the same category are to each other semantically and use this information to evaluate our model. We calculated the mean difference and average similarity values for each category to indicate how well our model describes that category.
%U https://aclanthology.org/2021.icon-main.34
%P 284-288
Markdown (Informal)
[Classifying Verses of the Quran using Doc2vec](https://aclanthology.org/2021.icon-main.34) (Alshammeri et al., ICON 2021)
ACL
- Menwa Alshammeri, Eric Atwell, and Mohammad Alsalka. 2021. Classifying Verses of the Quran using Doc2vec. In Proceedings of the 18th International Conference on Natural Language Processing (ICON), pages 284–288, National Institute of Technology Silchar, Silchar, India. NLP Association of India (NLPAI).