Ontology Enrichment by Extracting Hidden Assertional Knowledge from Text

Abstract —In this position paper we present a new approach for discovering some special classes of assertional knowledge in the text by using large RDF repositories, resulting in the extraction of new non-taxonomic ontological relations. Also we use inductive reasoning beside our approach to make it outperform. Then, we prepare a case study by applying our approach on sample data and illustrate the soundness of our proposed approach. Moreover in our point of view current LOD cloud is not a suitable base for our proposal in all informational domains. Therefore we figure out some directions based on prior works to enrich datasets of Linked Data by using web mining. The result of such enrichment can be reused for further relation extraction and ontology enrichment from unstructured free text documents. Keywords-Assertional knowledge; Linked Data; invisible information; ontological knowledge; web mining I. concepts of the ontology. Actually we see Linked Data as a I NTRODUCTION Information Extraction is categorized into three tasks [21]: Named Entity (in a nutshell NE) Recognition, Named Entity Disambiguation and Relation Extraction. Actually recognition of named entities deals with finding textual mentions of entities which belong to a set of categories including persons, organizations, places, etc. In disambiguation of named entities we relate the mentions of entities in the text to an external entity. Finally in relation extraction process we extract semantic relations between predefined named entities. By applying relation extraction process we can convert unstructured data (we mean free texts) into structured data. This makes it possible to apply so many algorithms in the field of data mining, question answering and semantic web [21]. To the best of our knowledge current methods for relation extraction are classified as follows: Manual relation extraction methods, supervised methods, semi-supervised methods and unsupervised methods. With emerging the web of Linked Data, so many researchers have tried to make use of its potential benefits [1, 2, 16, 17 and 30]. Also we believe that Linked Data has hidden potential benefits. There are some approaches which uses Linked Data to discover the relations between NE pairs in a text [3].