Natural language interface for Quran knowledge retrieval

With the introduction of semantic Web technology, recent researches has focuses on Natural Language Interface (NLI) with the aim of using unstructured natural language query to retrieved structured RDF data. These NLI researches focuses on semantically formulating natural language query to structured query manually, semi-automatic or automatically. Most of these systems are search like systems, where user’s natural language query is used to semantically formulate structured query. However, these systems rely on the presence of ontology concept in user’s query in order to formulate the natural language query to structured query and fails when concept is not found in the query. This paper proposed a natural language interface system that semantically formulate user’s natural language query either with presence of ontology concept in the query or otherwise. In this paper, a system-based suggestion approach is proposed as solution to semantically formulate natural language query when there is no ontology concept in the query. The system is based on using n-gram maximum likelihood estimation to automatically suggest to user possible structured query. The proposed natural language interface has improve the effectiveness retrieved result with 0.03 precision and 0.07 recall improvement.

PDF 32546.pdf Restricted to Repository staff only Download (170kB)

Actions (login required)

View Item