Send the link below via email or IMCopy
Present to your audienceStart remote presentation
- Invited audience members will follow you as you navigate and present
- People invited to a presentation do not need a Prezi account
- This link expires 10 minutes after you close the presentation
- A maximum of 30 users can follow your presentation
- Learn more about this feature in our knowledge base article
Copy of CS thesis 2013
Transcript of Copy of CS thesis 2013
Supervisor: Dr. Samir Al-Tartir
Faculty of Information Technology
Department of Computer Science Using Semantic Approaches to Answer Arabic Questions from the Holy Quran. Allah The Qur'an
itself History Governance Human rights Day-to-Day transactions Animal rights we are targeting a population of 1.5 billion muslims all over the world ...also we are targeting many others asking about Islam Qur'an is the main source where Muslims find their religious teachings, knowledge and rulings Motivation fatwa believe Financial affairs heritage prophets the here after as muslims the Qur'an was and will stay our number one source where we seek answers... still, no approach to answer real questions people may have ... Current approaches ربي يجازيك خير ربي يجازيك خير most approaches relay on a very naïve full match keyword search, one advancement was made by adding the root deriving aspect, this enhanced the search but never reached the level of semantics, also very far away from ontology. to test these search approaches we will search for a well known word Smarter engines results was... Semantically correlating concepts and features through the Qur'an verses.
Absence of a strong word manipulation layer.
Concentrating on syntax rather than semantics.
Absence of a strong, full and meaningful ontology layer.
Total absence of a question answering system. After examining these currently used Qur'an search engines, it was clear that all either didn't implement or poorly implemented these aspects: The computational Quranic linguistics team, University of LEEDS Dr. Sabri A. Mahmoud, Professor
ICS Department, King Fahd University of Petroleum and Minerals Dr. Husni A. AL-Muhtaseb
Assistant Professor, ICS Department,
King Fahd University of Petroleum &Minerals Dr. Samir Tartir
Philadelphia University, Amman, Jordan Me :) During this research we will be collaborating with... 1. Qurany subject browser.
2. Quranic Arabic corpus.
3. Tools on text mining the Qur'an. 75+ publications in...
Arabic Document Analysis
Arabic Writing Identification
Arabic Text Recognition 50+ publications in...
Natural Language Processing
Arabic OCR 8+ publications in...
Question answering systems
Semantic Web and ontology The (preprocessing / run-time processing) stages in our question answering system... synonyms generation 1 3 Root generation Ontology and semantics 2 Part of speech parser 4 5 many attempts was introduced to view the ontology of the Qur'an but non was a real ontology... ...one of our goals in this research is to build a semantic representation (ontology) of the Qur'an a real ontology representation would look more like this... no arabic representation, poor edge weighting very narrow, only talks about one topic, poor edge weighting Most of the current introduced approaches are taxonomy based but our work is ontology based filled with semantic relations Building a semantic representation (ontology) of the Qur'an.
Enforcing semantic aspects in the search layer of the question answering system.
Using Arabic WordNet repository for the Arabic language. This will help in generating synonyms, word roots, time tenses and many other forms of a particular given word, this will help in getting most of the targeted answers for a user question.
Building a question analysis layer that will parse the users question semantically to enhance our retrieving query.
A Phonetic Search layer will be embedded in the system to allow non-Arabic speakers to get more enhanced results. ex. will indicate a place, so only place related branch of the ontology will be used to answer the user question ex. will indicate a person so only human related branch of the ontology will be used to answer the user question Proposed contributions: Summary Part of speech parsing Our system Arabic language semantic strength Question answering Semantically related verses Wordnet, synonyms and root derivations Semantics and ontology Any questions??? M.Sc in CS thesis presentation www.altafsir.com www.alawfa.com www.ketaballah.net www.qurancomplex.org www.tanzil.net www.quranicresearcher.com www.alfanous.org www.nss.cm corpus.quran.com/ontology corpus.quran.com/ontology www.csc.mrc.ac.uk "AN ONTOLOGICAL MODEL FOR REPRESENTING SEMANTIC LEXICONS"
introduced by Dr. Maha Al-Yahya,
Head, Information Technology Department, King Saud University www.stick.ischool.umd.edu www.corpus.quran.com/ References
 The Holy Quran.
 Ibn-katheer, the Tafsir of Ibn Kathir, Damascus 1370.
 Ash-Shanqeetee, the Tafsir of Adwaa Al-Bayaan, Medina 1955.
 Tanveer Hussain, Quranic data and text resources, united kingdom. http://Quranicteachings.org/resources/
 K. Dukes, E. Atwell and N. Habash, Supervised Collaboration for Syntactic Annotation of Quranic Arabic, Language Resources and Evaluation Journal (LREJ), 2012.
 M.A. Yunus, R. Zainuddin, N. Abdullah, Semantic Speech Query via Stemmer for Quran Documents Results, Faculty of Computer Science and Information Technology, University of Malaya , Kuala Lumpur
 Bassam Hammo, Azzam Sleit, Mahmoud El-Haj, Effectiveness of Query Expansion in Searching the Holy Quran, Jordan University, King Abdullah II School for Information Technology.
 Kais Dukes, Eric Atwell and Abdul-Baquee M. Sharaf, Syntactic Annotation Guidelines for the Quranic Arabic Dependency Treebank, school of computing, University of Leeds, United Kingdom, 2012.
 E. Atwell, C. Brierley, K. Dukes, M. Sawalha, A. M. Sharaf, An Artificial Intelligence Approach to Arabic and Islamic Content on the Internet, National Information Technology Symposium (NITS), Riyadh, Saudi Arabia, 2011.
 Mohamad Noordin, Roslina Othman, An Information Retrieval System for Quranic Texts: A Proposed System Design, Faculty of ICT, International Islamic University Malaysia.
 Abraham Bernstein, Esther Kaufmann, Christian Kaiser, "Ginseng: A Guided Input Natural Language Search Engine for Querying Ontologies", Jena User Conference, Bristol, UK, May 2006.
 Lopez V., Pasin M. and Motta E., AquaLog: An Ontology-portable Question Answering System for the Semantic Web, European Semantic Web Conference, Greece, 2005.
 Pablo N. Mendes, Bobby McKnight, Amit P. Sheth and Jessica C. Kissinger, "Enabling Complex Queries For Genome Data Exploration", The IEEE Second International Conference on Semantic Computing (ICSC) 2008 in Santa Clara California.
 Resource Description Framework website, http://www.w3.org/RDF/
 Samir Tartir, Bobby McKnight and I. Budak Arpinar, SemanticQA: Web-Based Ontology-Driven Question Answering, In the 24th Annual ACM Symposium on Applied Computing, Waikiki Beach, Honolulu, Hawaii, USA, 2009.
 SPARQL Query Language for RDF website, http://www.w3.org/TR/rdfsparql-query/
 Noorhan Hassan Abbas, Quran „Search for a Concept Tool and Website, The University of Leeds, June, 2009.
 Samir Tartir, I. Budak Arpinar, Bobby McKnight, SemanticQA: Exploiting Semantic Associations for Cross-Document Question Answering, Philadelphia University, University of Georgia.
 William Black, Sabri Elkateb, Horacio Rodriguez, Musa Alkhalifa, Introducing the Arabic WordNet project, school of informatics, University of Manchester, University of Barcelona
 Qurany, http://Quranykeywords.appspot.com/
 Text mining the Quran, http://www.textminingtheQuran.com/
 Al MOYSAR Quranic search engine, http://moysar.com/searchq.php
 Quran corpus system, http://corpus.Quran.com/Qurandictionary.jsp
 Arabic corpus online system, http://arabicorpus.byu.edu
 The computational Quranic linguistics team, university of Leeds, http://www.comp.leeds.ac.uk/scsams/presentations/sharaf-uqu-2011.pdf.