Mining concepts from Wikipedia for ontology construction

The ongoing astounding growth of text data has created an enormous need for fast and efficient text mining algorithms. Traditional approaches for document representation are mostly based on the Bag of Words (BOW) model which takes a document as an unordered collection of words. However, when applied in fine-grained information discovery tasks, such as mining semantic relationships between concepts, sorely relying on the BOW representation may not be sufficient to identify all potential relationships since the resulting associations based on the BOW approach are limited to the concepts that appear in the document collection literally. In this paper, we attempt to complement existing information in the corpus by proposing a new hybrid approach, which mines semantic associations between concepts across multiple text units through incorporating extensive knowledge from Wikipedia. The experimental evaluation demonstrates that search performance has been significantly enhanced in terms of accuracy and coverage compared with a purely BOW-based approach and alternative solutions where only the article contents of Wikipedia or category information are considered.

With the advent of the Web and the explosion of available textual data, the field of domain ontology engineering has gained more and more importance. The last decade, several successful tools for automatically harvesting knowledge from web data have been developed, but the extraction of taxonomic and non taxonomic ontological relationships is still far from being fully solved. This paper describes a new approach which extracts ontological relations from Wikipedia. The non-taxonomic relations extraction process is performed by analyzing the titles which appear in each document of the studied corpus. This method is based on regular expressions which appear in titles and from which we can extract not only the two arguments of the relationships but also the labels which describe the relations. The resulting set of labels is used in order to retrieve new relations by analyzing the title hierarchy in each document. Other relations can be extracted from titles and subtitles containing only one term. An enrichment step is also applied by considering each term which appears as a relation argument of the extracted links in order to discover new concepts and new relations. The experiments have been performed on French Wikipedia articles related to the medical field. The precision and recall values are encouraging and seem to validate our approach.

2000

Ontologies have become an important means for structuring knowledge and building knowledge-intensive systems. For this purpose, efforts have been made to facilitate the ontology engineering process, in particular the acquisition of ontologies from domain texts. We present a general architecture for discovering conceptual structures and engineering ontologies. Based on our generic architecture we describe a case study for mining ontologies from text using methods based on dictionaries and natural language text. The case study has been carried out in the telecommunications domain. Supporting the overall text ontology engineering process, our comprehensive approach combines dictionary parsing mechanisms for acquiring a domain-specific concept taxonomy with a discovery mechanism for the acquisition of non-taxonomic conceptual relations.

2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings)(WI'06), 2006

Designing mechanisms for creating concept ontologies automatically is an important research problem. In this work we have proposed a rough-set based mechanism to generate concept ontologies with concepts mined from documents. When the concept ontology is mined from preclassified documents, the output signifies the core set of domain concepts and their interrelationships that define the categories, as well as the inter-category relationships. When the ontology is mined from a heterogeneous collection, the documents are first clustered into homogeneous groups and then mined for concepts. Rough set based lower and upper approximations have been used to identify core concepts and associated concepts for a domain or a group. The scheme has been tested over multiple domains.

International Conference on Knowledge Engineering and Ontology Development, 2010

Since its debut in 2001 Wikipedia has attracted the attention of many researchers in different fields. In recent years researchers in the area of ontology learning have realised the huge potential of Wikipedia as a source of semi-structured knowledge and several systems have used it as their main source of knowledge. However, the techniques used to extract semantic information vary greatly, as do the resulting ontologies. This paper introduces a framework to compare ontology learning systems that use Wikipedia as their main source of knowledge. Six prominent systems are compared and contrasted using the framework.

2012

In this paper, we present a new key term extraction system able to handle with the particularities of ''support documents''. Our system takes advantages of frequency-based and thesaurus-based approaches to recognize two different classes of key terms. On the one hand, it identifies multi-domain key terms of the collection using Wikipedia as knowledge resource. On the other hand, the system extracts specific key terms highly related with the context of a support document. We use the frequency in language as a criterion to detect and rank such terms. To prove the validity of our system we have designed a set of experiment using a Frequently Asked Questions (FAQ) collection of documents. Since our approach is generic, minor modifications should be undertaken to adapt the system to other kind of support documents. The empirical results evidence the validity of our approach.

2012

This paper presents methods for extraction of semantic relations between words. The methods rely on the k-nearest neighbor algorithms and two semantic similarity measures to extract relations from the abstracts of Wikipedia articles. We analyze the proposed methods and evaluate their performance. Precision of the extraction with the best method achieves 83%. We also present an open source system which effectively implements the described algorithms.

Expert Systems with Applications, 2014

Key concept extraction is a major step for ontology learning that aims to build an ontology by identifying relevant domain concepts and their semantic relationships from a text corpus. The success of ontology development using key concept extraction strongly relies on the degree of relevance of the key concepts identified. If the identified key concepts are not closely relevant to the domain, the constructed ontology will not be able to correctly and fully represent the domain knowledge. In this paper, we propose a novel method, named CFinder, for key concept extraction. Given a text corpus in the target domain, CFinder first extracts noun phrases using their linguistic patterns based on Part-Of-Speech (POS) tags as candidates for key concepts. To calculate the weights (or importance) of these candidates within the domain, CFinder combines their statistical knowledge and domain-specific knowledge indicating their relative importance within the domain. The calculated weights are further enhanced by considering an inner structural pattern of the candidates. The effectiveness of CFinder is evaluated with a recently developed ontology for the domain of 'emergency management for mass gatherings' against the state-of-the-art methods for key concept extraction including-Text2Onto, KP-Miner and Moki. The comparative evaluation results show that CFinder statistically significantly outperforms all the three methods in terms of F-measure and average precision.