Natural Language Interface for Quran Knowledge Retrieval

Abstract

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. The NLI researches focuses on semantically formulating natural language query either manually, semi-automatic or automatically. Most of these systems are search systems, where user’s natural language query is semantically formulated to structured query. However, these system rely on the presence of ontology concept in the query, in order to formulate the natural language query and it is consider failure when the concept is not found in the query. This paper proposed a natural language interface that semantically formulate user’s natural language query either with the presence of ontology concept in the query or otherwise. 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 the possible structured query. The proposed natural language interface has improve the effectiveness retrieved result with 0.03 precision and 0.07 recall improvement.