Design of Ontology-based Question Answering System for Incompleted Sentence Problem

Open

Rajif Agung Yunmar, I. Wayan Wiprayoga Wisesa

2019 IOP Conference Series: Earth and Environmental Science Vol. 258 Issue 1 Conference paper Cited by 1 SDG 16 Quartile

Abstract

Ontology-based Question Answering System (QAS) has advantage on representing semantic knowledge concept of an object, property, and relation between objects on a particular domain. Ontology-based QAS requires a proper definition of objects, properties, and their relationships in order to work correctly. It is very challenging topic for Bahasa Indonesia, especially when dealing with incomplete question sentences. For example: the sentence with no question word or no question object, or no obscure adverb question. This study designed an Ontology-based QAS that capable for dealing incomplete question sentence. Two approach method has been done to deal with the problem: First, designed an ontology that used a keyword property to find the question objective; Second, designed an architecture that transform the question in natural language into instruction that can be understood by computer. Experiment results shows that the ontology design plays an important role for Ontology-based QAS as well as system design. © Published under licence by IOP Publishing Ltd.

Affiliations

Informatics Engineering, Institut Teknologi Sumatera, Lampung Selatan, Indonesia

Research at a Glance

Premium content — register to unlock

Research at a Glance

Register to unlock

Topics & SDG Alignment

Premium content — register to unlock

Topics & SDG Alignment

Register to unlock

Collaboration

Premium content — register to unlock

Collaboration

Register to unlock

Author Profile (Selected)

Premium content — register to unlock

Author Profile (Selected)

Register to unlock

References Overview

Premium content — register to unlock

References Overview

Register to unlock

Journal & Source

Premium content — register to unlock

Journal & Source

Register to unlock

Metadata & Integrity

Premium content — register to unlock

Metadata & Integrity

Register to unlock