Abstract

Research on ontology is becoming increasingly widespread in the computer science community. The major problems in building ontologies are the bottleneck of knowledge acquisition and time-consuming construction of various ontologies for various domains/applications. Meanwhile moving toward automation of ontology construction is a solution.

We proposed an automatic ontology building approach. In this approach, the system starts from a small ontology kernel and constructs the ontology through text understanding automatically. The kernel contains the primitive concepts, relations and operators to build an ontology. The features of our proposed model are being domain/application independent, building ontologies upon a small primary kernel, learning words, concepts, taxonomic and non-taxonomic relations and axioms and applying a symbolic, hybrid ontology learning approach consisting of logical, linguistic based, template driven and semantic analysis methods.

Hasti is an ongoing project to implement and test the automatic ontology building approach. It extracts lexical and ontological knowledge from Persian (Farsi) texts.

In this paper, at first, we will describe some ontology engineering problems, which motivated our approach. In the next sections, after a brief description of Hasti, its features and its architecture, we will discuss its components in detail. In each part, the learning algorithms will be described. Then some experimental results will be discussed and at last, we will have an overview of related works and will introduce a general framework to compare ontology learning systems and will compare Hasti with related works according to the framework.

Article Outline

1. Introduction

1.1. Lacking of standards to integrate or reuse existing ontologies

1.2. Using fixed categories based on a single viewpoint

1.3. Absence of full automatic knowledge acquisition methods

2. The architecture of Hasti

2.1. The natural language processor

2.2. The working memory manager

2.3. The knowledge extractor

2.4. The knowledge base

2.5. The lexicon manager

2.6. The ontology manager

3. Supplementary components

3.1. Working memory

3.1.1. Text and sentence structures

3.1.2. Indexing structure

3.1.3. Hypothesis

3.1.4. List of primary ontels (LOPO)

3.2. The knowledge base

3.2.1. The lexicon

3.2.2. The ontology

3.2.3. The rule base

4. Functional components

4.1. The natural language processing component

4.1.1. Learning lexical knowledge

4.2. The knowledge extractor

4.2.1. Knowledge extraction at sentence level

4.2.2. Knowledge extraction at text level

4.3. The ontology manager

4.3.1. Clustering

4.3.2. Ontology refinement and reorganization

4.4. An example

4.4.1. A simple test

5. Experimental results

5.1. Evaluation

5.1.1. Phase one: converting sentences to sentence structures

5.1.2. Phase two: extracting ontological structures from SSTs

6. Discussion

6.1. Features of ontology learning systems

6.2. Comparison with related works

7. Conclusion and further works

References