Title: Arabic Question Answering System Using Graph Ontology
Abstract: The search engines are doing a great effort in getting answers for questions, especially, sophisticated answers. Question answering systems are used as modules of the search engines to enrich the search mechanism. This paper aims to present an Arabic question answering system using graph ontology, by using multiple semantic techniques. Graph ontology is used as the main source of getting answers, in addition to a web search API as an alternative path to get answers and enrich the ontology. The proposed system is tested on three datasets. The system achieved an accuracy (C@1) of 0.846 with an increase of 0.486 over similar systems and a recall of 0.958 in the second experiment, which is less than the compared systems by 0.008.
Publication Year: 2020
Publication Date: 2020-01-01
Language: en
Type: book-chapter
Indexed In: ['crossref']
Access and Citation
Cited By Count: 4
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot