Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.12358/20164
Title | An Ontology-Based Arabic Question Answering System |
---|---|
Title in Arabic | نظام عربي للاجابة على الاسئلة اعتمادا على الانتولوجيا |
Abstract |
Question Answering (QA) is a field that has been widely explored in previous research. However, research in Arabic QA is still limited and has not reached the same level of English QA due to the Arabic language specific challenges. Most importantly, existing research in Arabic QA has not explored the field of QA on the Semantic Web, and has mainly focused on information retrieval from unstructured Arabic documents. Nowadays, a huge amount of information is available on the Web in terms of RDF and OWL. The Web is evolving rapidly towards the notion of Linked Data where the data is linked by exploiting the Semantic Web technologies and standards. This information can be queried by using the standard SPARQL. However, naïve users who have no experience with Semantic Web cannot express their questions in SPARQL. This problem can be resolved by using Natural Language (NL) interfaces that translate NL queries to SPARQL. While many efforts explored the design of NL interfaces for the Semantic Web, none of these efforts, to our knowledge, considered the use of Arabic language which has unique characteristics. This work aims to make a step towards supporting Arabic QA on the Semantic Web. It introduces the QA system that can interface to any Arabic ontology, get a NL user query as an input and retrieves an answer from a RDF knowledge base. The core of the system is the approach we propose to translate Arabic NL queries to SPARQL. The approach makes intensive use of the ontology semantics to translate the user query to RDF triple patterns and infer any missing components to build up a complete SPARQL query. The proposed approach can process queries of different complexities and structures. The proposed system has been preliminary tested with a sample ontology and a testing set consisting of 30 different questions. Results have shown that the system can correctly answer 28 out of the 30 questions. |
Authors | |
Supervisors | |
Type | رسالة ماجستير |
Date | 2015 |
Language | English |
Publisher | الجامعة الإسلامية - غزة |
Citation | |
License | ![]() |
Collections | |
Files in this item | ||
---|---|---|
file_1.pdf | 3.621Mb |