Query translation using concepts similarity based on Quran ontology for cross-language information retrieval

Zulaini Yahya, Muhamad Taufik Abdullah, Azreen Azman, Abdul Kadir Rabiah

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

In Cross-Language Information Retrieval (CLIR) process, the translation effects have a direct impact on the accuracy of follow-up retrieval results. In dictionary-based approach, we are dealing with the words that have more than one meaning which can decrease the retrieval performance if the query translation return an incorrect translations. These issues need to be overcome using efficient technique. In this study we proposed a Cross-Language Information Retrieval (CLIR) method based on domain ontology using Quran concepts for disambiguating translation of the query and to improve the dictionary-based query translation. For experimentation, we use Quran ontology written in English and Malay languages as a bilingual parallelcorpora and Quran concepts as a resource for cross-language query translation along with dictionary-based translation. For evaluation, we measure the performance of three IR systems. IR1 is natural language query IR, IR2 is natural language query CLIR based on dictionary (as a Baseline) and IR3 is the retrieval of this research proposed method using Mean Average Precision (MAP) and average precision at 11 points of recall. The experimental result shows that our proposed method brings significant improvement in retrieval accuracy for English document collections, but deficient for Malay document collections. The proposed CLIR method can obtain query expansion effect and improve retrieval performance in certain language.

Original languageEnglish
Pages (from-to)889-897
Number of pages9
JournalJournal of Computer Science
Volume9
Issue number7
DOIs
Publication statusPublished - 2013
Externally publishedYes

Fingerprint

Query languages
Ontology
Glossaries

Keywords

  • Bilingual dictionary
  • English language
  • Malay language
  • Quran concepts
  • Quran ontology

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Query translation using concepts similarity based on Quran ontology for cross-language information retrieval. / Yahya, Zulaini; Abdullah, Muhamad Taufik; Azman, Azreen; Rabiah, Abdul Kadir.

In: Journal of Computer Science, Vol. 9, No. 7, 2013, p. 889-897.

Research output: Contribution to journalArticle

@article{79fd2efed9504496b15dcbe604cd58ab,
title = "Query translation using concepts similarity based on Quran ontology for cross-language information retrieval",
abstract = "In Cross-Language Information Retrieval (CLIR) process, the translation effects have a direct impact on the accuracy of follow-up retrieval results. In dictionary-based approach, we are dealing with the words that have more than one meaning which can decrease the retrieval performance if the query translation return an incorrect translations. These issues need to be overcome using efficient technique. In this study we proposed a Cross-Language Information Retrieval (CLIR) method based on domain ontology using Quran concepts for disambiguating translation of the query and to improve the dictionary-based query translation. For experimentation, we use Quran ontology written in English and Malay languages as a bilingual parallelcorpora and Quran concepts as a resource for cross-language query translation along with dictionary-based translation. For evaluation, we measure the performance of three IR systems. IR1 is natural language query IR, IR2 is natural language query CLIR based on dictionary (as a Baseline) and IR3 is the retrieval of this research proposed method using Mean Average Precision (MAP) and average precision at 11 points of recall. The experimental result shows that our proposed method brings significant improvement in retrieval accuracy for English document collections, but deficient for Malay document collections. The proposed CLIR method can obtain query expansion effect and improve retrieval performance in certain language.",
keywords = "Bilingual dictionary, English language, Malay language, Quran concepts, Quran ontology",
author = "Zulaini Yahya and Abdullah, {Muhamad Taufik} and Azreen Azman and Rabiah, {Abdul Kadir}",
year = "2013",
doi = "10.3844/jcssp.2013.889.897",
language = "English",
volume = "9",
pages = "889--897",
journal = "Journal of Computer Science",
issn = "1549-3636",
publisher = "Science Publications",
number = "7",

}

TY - JOUR

T1 - Query translation using concepts similarity based on Quran ontology for cross-language information retrieval

AU - Yahya, Zulaini

AU - Abdullah, Muhamad Taufik

AU - Azman, Azreen

AU - Rabiah, Abdul Kadir

PY - 2013

Y1 - 2013

N2 - In Cross-Language Information Retrieval (CLIR) process, the translation effects have a direct impact on the accuracy of follow-up retrieval results. In dictionary-based approach, we are dealing with the words that have more than one meaning which can decrease the retrieval performance if the query translation return an incorrect translations. These issues need to be overcome using efficient technique. In this study we proposed a Cross-Language Information Retrieval (CLIR) method based on domain ontology using Quran concepts for disambiguating translation of the query and to improve the dictionary-based query translation. For experimentation, we use Quran ontology written in English and Malay languages as a bilingual parallelcorpora and Quran concepts as a resource for cross-language query translation along with dictionary-based translation. For evaluation, we measure the performance of three IR systems. IR1 is natural language query IR, IR2 is natural language query CLIR based on dictionary (as a Baseline) and IR3 is the retrieval of this research proposed method using Mean Average Precision (MAP) and average precision at 11 points of recall. The experimental result shows that our proposed method brings significant improvement in retrieval accuracy for English document collections, but deficient for Malay document collections. The proposed CLIR method can obtain query expansion effect and improve retrieval performance in certain language.

AB - In Cross-Language Information Retrieval (CLIR) process, the translation effects have a direct impact on the accuracy of follow-up retrieval results. In dictionary-based approach, we are dealing with the words that have more than one meaning which can decrease the retrieval performance if the query translation return an incorrect translations. These issues need to be overcome using efficient technique. In this study we proposed a Cross-Language Information Retrieval (CLIR) method based on domain ontology using Quran concepts for disambiguating translation of the query and to improve the dictionary-based query translation. For experimentation, we use Quran ontology written in English and Malay languages as a bilingual parallelcorpora and Quran concepts as a resource for cross-language query translation along with dictionary-based translation. For evaluation, we measure the performance of three IR systems. IR1 is natural language query IR, IR2 is natural language query CLIR based on dictionary (as a Baseline) and IR3 is the retrieval of this research proposed method using Mean Average Precision (MAP) and average precision at 11 points of recall. The experimental result shows that our proposed method brings significant improvement in retrieval accuracy for English document collections, but deficient for Malay document collections. The proposed CLIR method can obtain query expansion effect and improve retrieval performance in certain language.

KW - Bilingual dictionary

KW - English language

KW - Malay language

KW - Quran concepts

KW - Quran ontology

UR - http://www.scopus.com/inward/record.url?scp=84880166941&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880166941&partnerID=8YFLogxK

U2 - 10.3844/jcssp.2013.889.897

DO - 10.3844/jcssp.2013.889.897

M3 - Article

AN - SCOPUS:84880166941

VL - 9

SP - 889

EP - 897

JO - Journal of Computer Science

JF - Journal of Computer Science

SN - 1549-3636

IS - 7

ER -