Arabic named entity recognition using artificial neural network

Naji F. Mohammed, Nazlia Omar

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Problem statement: Named Entity Recognition (NER) is a task to identify proper names as well as temporal and numeric expressions, in an open-domain text. The NER task can help to improve the performance of various Natural Language Processing (NLP) applications such as Information Extraction (IE), Information Retrieval (IR) and Question Answering (QA) tasks. This study discusses on the Named Entity Recognition of Arabic (NERA). The motivation is due to the lack of resources for Arabic named entities and to enhance the accuracy that has been reached in previous NERA systems. Approach: This system is designed based on neural network approach. The main task of neural network approach is to automatically learn to recognize component patterns and make intelligent decisions based on available data and it can also be applied to classify new information within large databases. The use of machine learning approach to classify NER from Arabic text based on neural network technique is proposed. Neural network approach has performed successfully in many areas of artificial intelligence. The system involves three stages: the first stage is pre-processing that cleans the collected data, the second involves converting Arabic letters to Roman alphabets and the final stage applies neural network to classify the collected data. Results: The accuracy of the system is 92 %. The system is compared with decision tree using the same data. The results showed that the neural network approach achieved better than decision tree. Conclusion: These results prove that our technique is capable to recognize named entities of Arabic texts.

Original languageEnglish
Pages (from-to)1285-1293
Number of pages9
JournalJournal of Computer Science
Volume8
Issue number8
DOIs
Publication statusPublished - 2012

Fingerprint

Neural networks
Decision trees
Processing
Information retrieval
Artificial intelligence
Learning systems

Keywords

  • Arabic
  • Arabic script
  • Artificial intelligence
  • Information extraction (IE)
  • Named entity recognition
  • Natural language processing
  • Neural network approach
  • Question answering (QA)

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Arabic named entity recognition using artificial neural network. / Mohammed, Naji F.; Omar, Nazlia.

In: Journal of Computer Science, Vol. 8, No. 8, 2012, p. 1285-1293.

Research output: Contribution to journalArticle

@article{a795413b39ec4f0cb41e94ecddb6a7fc,
title = "Arabic named entity recognition using artificial neural network",
abstract = "Problem statement: Named Entity Recognition (NER) is a task to identify proper names as well as temporal and numeric expressions, in an open-domain text. The NER task can help to improve the performance of various Natural Language Processing (NLP) applications such as Information Extraction (IE), Information Retrieval (IR) and Question Answering (QA) tasks. This study discusses on the Named Entity Recognition of Arabic (NERA). The motivation is due to the lack of resources for Arabic named entities and to enhance the accuracy that has been reached in previous NERA systems. Approach: This system is designed based on neural network approach. The main task of neural network approach is to automatically learn to recognize component patterns and make intelligent decisions based on available data and it can also be applied to classify new information within large databases. The use of machine learning approach to classify NER from Arabic text based on neural network technique is proposed. Neural network approach has performed successfully in many areas of artificial intelligence. The system involves three stages: the first stage is pre-processing that cleans the collected data, the second involves converting Arabic letters to Roman alphabets and the final stage applies neural network to classify the collected data. Results: The accuracy of the system is 92 {\%}. The system is compared with decision tree using the same data. The results showed that the neural network approach achieved better than decision tree. Conclusion: These results prove that our technique is capable to recognize named entities of Arabic texts.",
keywords = "Arabic, Arabic script, Artificial intelligence, Information extraction (IE), Named entity recognition, Natural language processing, Neural network approach, Question answering (QA)",
author = "Mohammed, {Naji F.} and Nazlia Omar",
year = "2012",
doi = "10.3844/jcssp.2012.1285.1293",
language = "English",
volume = "8",
pages = "1285--1293",
journal = "Journal of Computer Science",
issn = "1549-3636",
publisher = "Science Publications",
number = "8",

}

TY - JOUR

T1 - Arabic named entity recognition using artificial neural network

AU - Mohammed, Naji F.

AU - Omar, Nazlia

PY - 2012

Y1 - 2012

N2 - Problem statement: Named Entity Recognition (NER) is a task to identify proper names as well as temporal and numeric expressions, in an open-domain text. The NER task can help to improve the performance of various Natural Language Processing (NLP) applications such as Information Extraction (IE), Information Retrieval (IR) and Question Answering (QA) tasks. This study discusses on the Named Entity Recognition of Arabic (NERA). The motivation is due to the lack of resources for Arabic named entities and to enhance the accuracy that has been reached in previous NERA systems. Approach: This system is designed based on neural network approach. The main task of neural network approach is to automatically learn to recognize component patterns and make intelligent decisions based on available data and it can also be applied to classify new information within large databases. The use of machine learning approach to classify NER from Arabic text based on neural network technique is proposed. Neural network approach has performed successfully in many areas of artificial intelligence. The system involves three stages: the first stage is pre-processing that cleans the collected data, the second involves converting Arabic letters to Roman alphabets and the final stage applies neural network to classify the collected data. Results: The accuracy of the system is 92 %. The system is compared with decision tree using the same data. The results showed that the neural network approach achieved better than decision tree. Conclusion: These results prove that our technique is capable to recognize named entities of Arabic texts.

AB - Problem statement: Named Entity Recognition (NER) is a task to identify proper names as well as temporal and numeric expressions, in an open-domain text. The NER task can help to improve the performance of various Natural Language Processing (NLP) applications such as Information Extraction (IE), Information Retrieval (IR) and Question Answering (QA) tasks. This study discusses on the Named Entity Recognition of Arabic (NERA). The motivation is due to the lack of resources for Arabic named entities and to enhance the accuracy that has been reached in previous NERA systems. Approach: This system is designed based on neural network approach. The main task of neural network approach is to automatically learn to recognize component patterns and make intelligent decisions based on available data and it can also be applied to classify new information within large databases. The use of machine learning approach to classify NER from Arabic text based on neural network technique is proposed. Neural network approach has performed successfully in many areas of artificial intelligence. The system involves three stages: the first stage is pre-processing that cleans the collected data, the second involves converting Arabic letters to Roman alphabets and the final stage applies neural network to classify the collected data. Results: The accuracy of the system is 92 %. The system is compared with decision tree using the same data. The results showed that the neural network approach achieved better than decision tree. Conclusion: These results prove that our technique is capable to recognize named entities of Arabic texts.

KW - Arabic

KW - Arabic script

KW - Artificial intelligence

KW - Information extraction (IE)

KW - Named entity recognition

KW - Natural language processing

KW - Neural network approach

KW - Question answering (QA)

UR - http://www.scopus.com/inward/record.url?scp=84864913972&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864913972&partnerID=8YFLogxK

U2 - 10.3844/jcssp.2012.1285.1293

DO - 10.3844/jcssp.2012.1285.1293

M3 - Article

VL - 8

SP - 1285

EP - 1293

JO - Journal of Computer Science

JF - Journal of Computer Science

SN - 1549-3636

IS - 8

ER -