Home   >   CSC-OpenAccess Library   >    Manuscript Information
An Efficient Semantic Relation Extraction Method For Arabic Texts Based On Similarity Measures
Abeer Alarfaj, Abdulmalik Alsalamn
Pages - 22 - 38     |    Revised - 31-12-2019     |    Published - 01-02-2020
Volume - 9   Issue - 1    |    Publication Date - February 2020  Table of Contents
Relation Extraction, Arabic NLP, Arabic Semantic Relation Extraction, Concept Context, Semantic Similarity Measures.
Semantic relation extraction is an important component of ontologies that can support many applications e.g. text mining, question answering, and information extraction. However, extracting semantic relations between concepts is not trivial and one of the main challenges in Natural Language Processing (NLP) Field. In this paper, we propose a method for semantic relation extraction between concepts. The method relies on the definition of concept context and the semantic similarity measures to extract relations from domain corpus. In this work, we implemented algorithm for concept context construction and for similarity computation based on different semantic similarity measures. We analyze the proposed methods and evaluate their performance. The preliminary experiments showed that the best results precision of 83% are obtained with Lin measure at minimum confidence =0.50 and precision of 85% with the Cosine and Jaccard similarity measures. The main advantage is the automatic and unsupervised operation; it doesn't need any pre labeled training data. Also used effectively for relation extraction in various domains. The results show the high effectiveness of the proposed approach to extract relations for Arabic ontology construction.
1 Google Scholar 
2 Semantic Scholar 
3 refSeek 
4 Scribd 
5 SlideShare 
A.Al-Arfaj and A. Al-Salman. (0014). "Towards Ontology Construction from Arabic Texts- A Proposed Framework" in Proceeding of The 14th IEEE International Conference on Computer and Information Technology (CIT 2014), 2014, pp. 737-742.
A.Alotayq. "Extracting relations between Arabic named entities", Lecture Notes in Computer Science, vol 8082, Springer-Verlag, Berlin Heidelberg, Pilsen, pp.265-271, 2013.
D. Lin., S. Zhao., L. Qin and M. Zhou. "Identifying synonyms among distributionally similar words," in Proceeding of 18th International Joint Conference on Artificial Intelligence (IJCAI), 2003, pp. 1492-1493.
F. Harrag., A. Alothaim., A. Abanmy., F. Alomaigan and S. Alsalehi. " Ontology Extraction Approach for Prophetic Narration (Hadith) using Association Rules.. International Journal on Islamic Applications in Computer Science And Technology, 1(2), pp. 48-57, 2013.
H. Haddad., J. Chevallet and M. Bruandet. "Relations between Terms Discovered by Association Rules," in Proceeding of 4th European Conference on Principles and Practices of Knowledge Discovery in Database (PKDD2000), Workshop on Machine Learning and Textual Information Access, Lyon France, 2000.
I.Bounhas , B. Elayeb ., F. Evrard and Y. Slimani. "ArabOnto: Experimenting a new distributional approach for building Arabic ontological resources." International Journal of Metadata, Semantics and Ontologies (IJMSO), 6(2), pp. 81 - 95, 2011.
I.Sarhan., Y. El-Sonbaty and M. El-Nasr. "Semi-Supervised Pattern-Based Algorithm for Arabic Relation Extraction". In proceeding of IEEE 08th International Conference on Tools with Artificial Intelligence (ICTAI), San Jose, CA, USA, 2016 pp. 177-183.
J.R. Curran and M. Moens. "Improvements in automatic thesaurus extraction," in Proceedings of the ACL-02 Workshop on Unsupervised Lexical Acquisition, 2002, pp. 59-66.
L. Meng., R. Huang and J. Gu. "A Review of Semantic Similarity Measures in WordNet." International Journal of Hybrid Information Technology. 6(1), pp. 1-12, 2013.
M. Al-Yahya., L. Aldhubayi and S. Al-Malak. "A Pattern-Based Approach to Semantic Relation Extraction Using a Seed Ontology," in Proceeding of IEEE International Conference on Semantic Computing, Newport Beach, California, 2014, pp,96-99.
M. AL-Zamil and G. Al-Radaideh. "Automatic Extraction of Ontological Relations from Arabic Text." Journal of King Saud University - Computer and Information Sciences,26(4),pp. 462-472, 2014.
N. Taghizadeha., H. Failia,H and J. Malekib. "Cross-Language Learning for Arabic Relation Extraction"., Procedia Computer Science, 140, pp. 190-197 . 2018.
O. Ferret. " Testing semantic similarity measures for extracting synonyms from a corpus," in Proceeding of 7th Conference on International Language Resources and Evaluation (LREC), Valeeta, Malta, 2010, PP. 3338-3343.
P. Cimiano. "Ontology Learning and Population from Text: Algorithms, Evaluation and Applications", in Studies in Philosophy and Religion, Springer, 2006.
S. El-salam., E. El Houby., A. Al Sammak and T. El-Shishtawy. " Extracting Arabic relations from the web". International Journal of Computer Science & Information Technology (IJCSIT), vol 8, no 1,pp. 85-102, 2016.
W. Lahbib., I. Bounhas., B. Elayeb., F. Evrard and Y. Slimani. "A Hybrid Approach for Arabic Semantic Relation Extraction," in Proceeding of The 00th International Florida Artificial Intelligence Research Society (FLAIRS), 2013,pp. 315-320.
Dr. Abeer Alarfaj
Department of Computer Sciences, College of Computer and Information Sciences, Princess Nora Bint AbdulRahman University - Saudi Arabia
Dr. Abdulmalik Alsalamn
Department of Computer Science, College of Computer and Information Sciences, King Saud University - Saudi Arabia