Khaleel Al-Rababah - Academia.edu (original) (raw)

Uploads

Papers by Khaleel Al-Rababah

Research paper thumbnail of Classifying Arabic Text Using KNN Classifier

International Journal of Advanced Computer Science and Applications, 2016

Research paper thumbnail of The Impact of Indexing Approaches on Arabic Text Classification

This paper investigates the impact of using different indexing approaches (full-word, stem, and r... more This paper investigates the impact of using different indexing approaches (full-word, stem, and root) when classifying Arabic text. In this study, the naïve Bayes classifier is used to construct the multinomial classification models and is evaluated using stratified k-fold cross-validation (k ranges from 2 to 10). It is also uses a corpus that consists of 1000 normalized Arabic documents. The results of one experiment in this study show that significant accuracy improvements have occurred when the full-word form is used in most k-folds. Further experiments show that the classifier has achieved the highest accuracy in the 8-fold by using 7/8–1/8 train/test ratio, despite the indexing approach being used. The overall results of this study show that the classifier has achieved the maximum micro-average accuracy 99.36%, either by using the full-word form or the stem form. This proves that the stem is a better choice to use when classifying Arabic text, because it makes the corpus dataset smaller and this will enhance both the processing time and storage utilization, and achieve the highest level of accuracy.

Research paper thumbnail of The effect of fullword, stem, and root as index-term on Arabic information retrieval

u l l w o r d , S t e m , a n d R o o t a s I n d e x -T e r m o n A r a b i c I n f o r m a t i ... more u l l w o r d , S t e m , a n d R o o t a s I n d e x -T e r m o n A r a b i c I n f o r m a t i o n R e t r i e v a l B y B a s e l B a n i -I s m a i l , K h a l e e l A l -R a b a b a h , S a f w a n S h a t n a w i S u l t a n Q a b o o s U n i v e r s i t y , O m a n Abstracts -In this research, we studied the performance of Arabic information retrieval system using different indexing approaches (fullword, stem, and root); the system used 50 queries tested against 1000 text documents collected from various Arabic newspapers web sites. The vector space model and cosine similarity measure were used to implement the system. We evaluate the system using R-precision measure. The results for our system show that the stem is more efficient in terms of both storage space requirement and query processing time compared to the other types of index-term. The results also show that the fullword takes the largest disk space and performs the worst for the query processing. The experimental results demonstrate that the fullword search gives the best retrieval performance overall other search methods; in addition the stem outperforms the root.

Research paper thumbnail of Applying a novel clustering technique based on FP-tree to university timetabling problem: A case study

The 2010 International Conference on Computer Engineering & Systems, 2010

In this study, we propose a clustering technique based on FP-tree algorithm to group students bas... more In this study, we propose a clustering technique based on FP-tree algorithm to group students based on the intended courses they will register for a given next semester. The goal of this clustering is to solve the problem of course's time scheduling that we encountered in previous semesters which prevented students from enrolling in some of these courses as they

Research paper thumbnail of A comparison study of some Arabic root finding algorithms

Journal of the American Society for Information Science and Technology, 2010

Abstract Arabic has a complex structure, which makes it difficult to apply natural language proce... more Abstract Arabic has a complex structure, which makes it difficult to apply natural language processing (NLP). Much research on Arabic NLP (ANLP) does exist; however, it is not as mature as that of other languages. Finding Arabic roots is an important step toward conducting effective research on most of ANLP applications. The authors have studied and compared six root-finding algorithms with success rates of over 90%. All algorithms of this study did not use the same testing corpus and/or benchmarking measures. They unified ...

Research paper thumbnail of Identifying significant single phrases in submitted free-Order arabic natural language questions

Information Society (i- …, 2011

... AbdelMahdi Saleh AI-Rababah Faculty of Information Systems and Technology University of Banki... more ... AbdelMahdi Saleh AI-Rababah Faculty of Information Systems and Technology University of Banking and Financial Sciences Amman, Jordan ... in sales department IJ.JJ ."..JI 0,lJ J f'1!)J "L..... 2.( Give names and numbers and addresses for employees and their salary). ...

Research paper thumbnail of An Arabic Language Interface to Databases Using a Morphologically-based Lexicon, Language Indicators and POS Tagging

In this paper, we propose an Arabic Natural Language Interface to Databases (ANLIDB), The ANLIDB ... more In this paper, we propose an Arabic Natural Language Interface to Databases (ANLIDB), The ANLIDB can respond to ill-formed questions submitted by users by bringing those questions to syntactically accepted questions. The ANLIDB also implements algorithms for extracting significant single and multiple phrases from Arabic natural language questions submitted to the database and then constructing and executing SQL questions. In this paper, we are dealing with Arabic language questions. An Arabic natural language (ANL) question is accepted as an input and then outputs all possible relations and its corresponding attributes. Arabic morphological, ontological, and syntactical analyses were applied in this paper. A lexicon derived from the database was created, and a simple part-of-speech (PoS) was implemented as well. The system shows high rates of success in identifying relations, correct mapping of attributes, and constructing and executing SQL statements.

Research paper thumbnail of Classifying Arabic Text Using KNN Classifier

International Journal of Advanced Computer Science and Applications, 2016

Research paper thumbnail of The Impact of Indexing Approaches on Arabic Text Classification

This paper investigates the impact of using different indexing approaches (full-word, stem, and r... more This paper investigates the impact of using different indexing approaches (full-word, stem, and root) when classifying Arabic text. In this study, the naïve Bayes classifier is used to construct the multinomial classification models and is evaluated using stratified k-fold cross-validation (k ranges from 2 to 10). It is also uses a corpus that consists of 1000 normalized Arabic documents. The results of one experiment in this study show that significant accuracy improvements have occurred when the full-word form is used in most k-folds. Further experiments show that the classifier has achieved the highest accuracy in the 8-fold by using 7/8–1/8 train/test ratio, despite the indexing approach being used. The overall results of this study show that the classifier has achieved the maximum micro-average accuracy 99.36%, either by using the full-word form or the stem form. This proves that the stem is a better choice to use when classifying Arabic text, because it makes the corpus dataset smaller and this will enhance both the processing time and storage utilization, and achieve the highest level of accuracy.

Research paper thumbnail of The effect of fullword, stem, and root as index-term on Arabic information retrieval

u l l w o r d , S t e m , a n d R o o t a s I n d e x -T e r m o n A r a b i c I n f o r m a t i ... more u l l w o r d , S t e m , a n d R o o t a s I n d e x -T e r m o n A r a b i c I n f o r m a t i o n R e t r i e v a l B y B a s e l B a n i -I s m a i l , K h a l e e l A l -R a b a b a h , S a f w a n S h a t n a w i S u l t a n Q a b o o s U n i v e r s i t y , O m a n Abstracts -In this research, we studied the performance of Arabic information retrieval system using different indexing approaches (fullword, stem, and root); the system used 50 queries tested against 1000 text documents collected from various Arabic newspapers web sites. The vector space model and cosine similarity measure were used to implement the system. We evaluate the system using R-precision measure. The results for our system show that the stem is more efficient in terms of both storage space requirement and query processing time compared to the other types of index-term. The results also show that the fullword takes the largest disk space and performs the worst for the query processing. The experimental results demonstrate that the fullword search gives the best retrieval performance overall other search methods; in addition the stem outperforms the root.

Research paper thumbnail of Applying a novel clustering technique based on FP-tree to university timetabling problem: A case study

The 2010 International Conference on Computer Engineering & Systems, 2010

In this study, we propose a clustering technique based on FP-tree algorithm to group students bas... more In this study, we propose a clustering technique based on FP-tree algorithm to group students based on the intended courses they will register for a given next semester. The goal of this clustering is to solve the problem of course's time scheduling that we encountered in previous semesters which prevented students from enrolling in some of these courses as they

Research paper thumbnail of A comparison study of some Arabic root finding algorithms

Journal of the American Society for Information Science and Technology, 2010

Abstract Arabic has a complex structure, which makes it difficult to apply natural language proce... more Abstract Arabic has a complex structure, which makes it difficult to apply natural language processing (NLP). Much research on Arabic NLP (ANLP) does exist; however, it is not as mature as that of other languages. Finding Arabic roots is an important step toward conducting effective research on most of ANLP applications. The authors have studied and compared six root-finding algorithms with success rates of over 90%. All algorithms of this study did not use the same testing corpus and/or benchmarking measures. They unified ...

Research paper thumbnail of Identifying significant single phrases in submitted free-Order arabic natural language questions

Information Society (i- …, 2011

... AbdelMahdi Saleh AI-Rababah Faculty of Information Systems and Technology University of Banki... more ... AbdelMahdi Saleh AI-Rababah Faculty of Information Systems and Technology University of Banking and Financial Sciences Amman, Jordan ... in sales department IJ.JJ ."..JI 0,lJ J f'1!)J "L..... 2.( Give names and numbers and addresses for employees and their salary). ...

Research paper thumbnail of An Arabic Language Interface to Databases Using a Morphologically-based Lexicon, Language Indicators and POS Tagging

In this paper, we propose an Arabic Natural Language Interface to Databases (ANLIDB), The ANLIDB ... more In this paper, we propose an Arabic Natural Language Interface to Databases (ANLIDB), The ANLIDB can respond to ill-formed questions submitted by users by bringing those questions to syntactically accepted questions. The ANLIDB also implements algorithms for extracting significant single and multiple phrases from Arabic natural language questions submitted to the database and then constructing and executing SQL questions. In this paper, we are dealing with Arabic language questions. An Arabic natural language (ANL) question is accepted as an input and then outputs all possible relations and its corresponding attributes. Arabic morphological, ontological, and syntactical analyses were applied in this paper. A lexicon derived from the database was created, and a simple part-of-speech (PoS) was implemented as well. The system shows high rates of success in identifying relations, correct mapping of attributes, and constructing and executing SQL statements.