Unsupervised concept hierarchy induction based on islamic glossary

Ammar Abdulateef Ali, Saidah Saad

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A machine-readable dictionary (MRD) is an electronic dictionary that enables query processing. One of the common processing tasks that has been widely applied is Concept Hierarchy Induction which aims at identifying concepts with its corresponding taxonomies such as named entities, synonyms and hyponyms. The Islamic domain contains a variety of concepts that are associated with numerous taxonomies. The existing concept hierarchy approaches for Islamic domain are using limited linguistic patterns. This study aims to propose an unsupervised concept hierarchy induction for the Islamic domain by extending the patterns and rules. In fact, Term Frequency-Inverse Document Frequency (TF-IDF) was carried out in order to identify the most frequently used concepts. Furthermore, two syntactical features were used including POS tagging and chunk parser in order to identify the tagging for each word (e.g. verb, noun, adjective, etc.) and extracting Noun Phrases (NP). Hence, the proposed extension patterns aim at utilize lexico-syntactic patterns to induce the concept hierarchy. The evaluation was performed using precision method by identifying the number of correctly extracted concepts and relation between them. Moreover, an expert review evaluation was performed by an expert in the Islamic domain. The experimental results showed that the proposed method achieved 82% precision. That demonstrates the usefulness of extending patterns for the Islamic domain.

Original languageEnglish
Pages (from-to)8505-8510
Number of pages6
JournalARPN Journal of Engineering and Applied Sciences
Volume11
Issue number13
Publication statusPublished - 2016

Fingerprint

Taxonomies
Glossaries
Query processing
Syntactics
Linguistics
Processing

Keywords

  • Concept hierarchy
  • Lexico-syntactic patterns
  • Ontology
  • Terminology extraction

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Unsupervised concept hierarchy induction based on islamic glossary. / Ali, Ammar Abdulateef; Saad, Saidah.

In: ARPN Journal of Engineering and Applied Sciences, Vol. 11, No. 13, 2016, p. 8505-8510.

Research output: Contribution to journalArticle

@article{80e349c423ee4f96930a6ec0f5d9ae8d,
title = "Unsupervised concept hierarchy induction based on islamic glossary",
abstract = "A machine-readable dictionary (MRD) is an electronic dictionary that enables query processing. One of the common processing tasks that has been widely applied is Concept Hierarchy Induction which aims at identifying concepts with its corresponding taxonomies such as named entities, synonyms and hyponyms. The Islamic domain contains a variety of concepts that are associated with numerous taxonomies. The existing concept hierarchy approaches for Islamic domain are using limited linguistic patterns. This study aims to propose an unsupervised concept hierarchy induction for the Islamic domain by extending the patterns and rules. In fact, Term Frequency-Inverse Document Frequency (TF-IDF) was carried out in order to identify the most frequently used concepts. Furthermore, two syntactical features were used including POS tagging and chunk parser in order to identify the tagging for each word (e.g. verb, noun, adjective, etc.) and extracting Noun Phrases (NP). Hence, the proposed extension patterns aim at utilize lexico-syntactic patterns to induce the concept hierarchy. The evaluation was performed using precision method by identifying the number of correctly extracted concepts and relation between them. Moreover, an expert review evaluation was performed by an expert in the Islamic domain. The experimental results showed that the proposed method achieved 82{\%} precision. That demonstrates the usefulness of extending patterns for the Islamic domain.",
keywords = "Concept hierarchy, Lexico-syntactic patterns, Ontology, Terminology extraction",
author = "Ali, {Ammar Abdulateef} and Saidah Saad",
year = "2016",
language = "English",
volume = "11",
pages = "8505--8510",
journal = "ARPN Journal of Engineering and Applied Sciences",
issn = "1819-6608",
publisher = "Asian Research Publishing Network (ARPN)",
number = "13",

}

TY - JOUR

T1 - Unsupervised concept hierarchy induction based on islamic glossary

AU - Ali, Ammar Abdulateef

AU - Saad, Saidah

PY - 2016

Y1 - 2016

N2 - A machine-readable dictionary (MRD) is an electronic dictionary that enables query processing. One of the common processing tasks that has been widely applied is Concept Hierarchy Induction which aims at identifying concepts with its corresponding taxonomies such as named entities, synonyms and hyponyms. The Islamic domain contains a variety of concepts that are associated with numerous taxonomies. The existing concept hierarchy approaches for Islamic domain are using limited linguistic patterns. This study aims to propose an unsupervised concept hierarchy induction for the Islamic domain by extending the patterns and rules. In fact, Term Frequency-Inverse Document Frequency (TF-IDF) was carried out in order to identify the most frequently used concepts. Furthermore, two syntactical features were used including POS tagging and chunk parser in order to identify the tagging for each word (e.g. verb, noun, adjective, etc.) and extracting Noun Phrases (NP). Hence, the proposed extension patterns aim at utilize lexico-syntactic patterns to induce the concept hierarchy. The evaluation was performed using precision method by identifying the number of correctly extracted concepts and relation between them. Moreover, an expert review evaluation was performed by an expert in the Islamic domain. The experimental results showed that the proposed method achieved 82% precision. That demonstrates the usefulness of extending patterns for the Islamic domain.

AB - A machine-readable dictionary (MRD) is an electronic dictionary that enables query processing. One of the common processing tasks that has been widely applied is Concept Hierarchy Induction which aims at identifying concepts with its corresponding taxonomies such as named entities, synonyms and hyponyms. The Islamic domain contains a variety of concepts that are associated with numerous taxonomies. The existing concept hierarchy approaches for Islamic domain are using limited linguistic patterns. This study aims to propose an unsupervised concept hierarchy induction for the Islamic domain by extending the patterns and rules. In fact, Term Frequency-Inverse Document Frequency (TF-IDF) was carried out in order to identify the most frequently used concepts. Furthermore, two syntactical features were used including POS tagging and chunk parser in order to identify the tagging for each word (e.g. verb, noun, adjective, etc.) and extracting Noun Phrases (NP). Hence, the proposed extension patterns aim at utilize lexico-syntactic patterns to induce the concept hierarchy. The evaluation was performed using precision method by identifying the number of correctly extracted concepts and relation between them. Moreover, an expert review evaluation was performed by an expert in the Islamic domain. The experimental results showed that the proposed method achieved 82% precision. That demonstrates the usefulness of extending patterns for the Islamic domain.

KW - Concept hierarchy

KW - Lexico-syntactic patterns

KW - Ontology

KW - Terminology extraction

UR - http://www.scopus.com/inward/record.url?scp=84978180088&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978180088&partnerID=8YFLogxK

M3 - Article

VL - 11

SP - 8505

EP - 8510

JO - ARPN Journal of Engineering and Applied Sciences

JF - ARPN Journal of Engineering and Applied Sciences

SN - 1819-6608

IS - 13

ER -