Hamdelsayed, MA and Atwell, ES orcid.org/0000-0001-9395-3764 (2016) Using Arabic Numbers (Singular, Dual, and Plurals) Patterns To Enhance Question Answering System Results. In: IMAN'2016 4th International Conference on Islamic Applications in Computer Science and Technologies. IMAN'2016 4th International Conference on Islamic Applications in Computer Science and Technologies, 20-22 Dec 2016, Khartoum, Sudan.
Abstract
In the field of information retrieval, it is very difficult to answer the question entered by the user, because the search engine retrieve a ranked documents that contain any key word or phrase inside the documents, this need another extra effort to search the answer inside the documents, and there may be no answer. The alternative of search engine is a question answering system, which it retrieves the exact answer of the question in the natural language if found. A question answering system accepts the question in the natural, then many processes were done to extract the exact answer. In general a question answering system is composed of three main components: question classification module, information retrieval module and answer extraction module. A question answering system is applied in holy Quran which written and cited in Arabic language, some characteristic of the Arabic language were used to enhance the answer extraction, one of these important characteristics is numbering, singular, dual and plural. A prototype build uses special pattern used to process the number in Arabic language, which enhance the answers by adding more words and meaning. A corpus of questions and its answers from holy Quran used to test and answers the question.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Keywords: | question answering system; corpus; Quran; Arabic language; natural language processing (NLP) |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 30 Mar 2017 09:15 |
Last Modified: | 14 Aug 2019 15:03 |
Status: | Published |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:112954 |