OntologyLine: A New Framework for Learning Non-taxonomic Relations of Domain Ontology

Domain Ontology learning has been introduced as a technology that aims at reducing the bottleneck of knowledge acquisition in the construction of domain ontologies. However, the discovery and the labelling of non-taxonomic relations have been identified as one of the most difficult problems in this learning process. In this paper, we propose OntologyLine, a new system for discovering non-taxonomic relations and building domain ontology from scratch. The proposed system is based on adapting Open Information Extraction algorithms to extract and label relations between domain concepts. OntologyLine was tested in two different domains: the financial and cancer domains. It was evaluated against gold standard ontology and was compared to state-of-the-art ontology learning algorithm. The experimental results show that OntologyLine is more effective for acquiring non-taxonomic relations and gives better results in terms of precision, recall and F-measure.

[1]  Gregory Grefenstette.  Short Query Linguistic Expansion Techniques: Palliating One-Word Queries by Providing Intermediate Structure to Text , 1997, SCIE.

[2]  Steffen Staab,et al.  Taxonomy Learning - Factoring the Structure of a Taxonomy into a Semantic Classification Decision , 2002, COLING.

[3]  Soon Myoung Chung,et al.  Text Clustering with Feature Selection by Using Statistical Data , 2008, IEEE Transactions on Knowledge and Data Engineering.

[4]  Brahim Ouhbi,et al.  A New Methodology for Domain Ontology Construction from the Web , 2011, Int. J. Artif. Intell. Tools.

[5]  Oren Etzioni,et al.  Identifying Relations for Open Information Extraction , 2011, EMNLP.

[6]  Steffen Staab,et al.  Semi-Automatic Engineering of Ontologies from Text , 2000, ICSE 2000.

[7]  Raphael Volz,et al.  The Ontology Extraction & Maintenance Framework Text-To-Onto , 2001 .

[8]  Ah-Hwee Tan,et al.  Mining ontological knowledge from domain-specific text documents , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[9]  Josep Domingo-Ferrer,et al.  Semantic variance: An intuitive measure for ontology accuracy evaluation , 2015, Eng. Appl. Artif. Intell..

[10]  Oren Etzioni,et al.  Open Information Extraction from the Web , 2007, CACM.

[11]  Paulo Novais,et al.  PARNT: A Statistic based Approach to Extract Non-Taxonomic Relationships of Ontologies from Text , 2013, 2013 10th International Conference on Information Technology: New Generations.

[12]  Philipp Cimiano,et al.  Ontology Learning from Text: Methods, Evaluation and Applications , 2005 .

[13]  Steven Skiena,et al.  Concordance-Based Entity-Oriented Search , 2007, IEEE/WIC/ACM International Conference on Web Intelligence (WI'07).

[14]  Lili Mou,et al.  Learning Non-Taxonomic Relations on Demand for Ontology Extension , 2014, Int. J. Softw. Eng. Knowl. Eng..

[15]  Analía Amandi,et al.  Supporting the discovery and labeling of non-taxonomic relationships in ontology learning , 2009, Expert Syst. Appl..

[16]  Steffen Staab,et al.  Ontology Learning for the Semantic Web , 2002, IEEE Intell. Syst..

[17]  Jianhua Chen,et al.  Learning non-taxonomical semantic relations from domain texts , 2011, Journal of Intelligent Information Systems.

[18]  Flavius Frasincar,et al.  A semantic approach for extracting domain taxonomies from text , 2014, Decis. Support Syst..

[19]  Soon-Young Huh,et al.  Automatic generation of concept hierarchies using WordNet , 2008, Expert Syst. Appl..

[20]  Jean-Paul Haton,et al.  WSIM : une méthode de détection de thème fondée sur la similarité entre mots , 2002, JEPTALNRECITAL.

[21]  Pradipta Maji,et al.  Gene ontology based quantitative index to select functionally diverse genes , 2014, Int. J. Mach. Learn. Cybern..

[22]  Luciano Del Corro,et al.  ClausIE: clause-based open information extraction , 2013, WWW.

[23]  Mohammed Bennamoun,et al.  Acquiring Semantic Relations Using the Web for Constructing Lightweight Ontologies , 2009, PAKDD.

[24]  Xia Wang,et al.  Decision support in e-business based on assessing similarities between ontologies , 2012, Knowl. Based Syst..

[25]  David Sánchez,et al.  Learning non-taxonomic relationships from web documents for domain ontology construction , 2008, Data Knowl. Eng..

[26]  Phayung Meesad,et al.  Comparison of hybrid feature selection models on gene expression data , 2010, 2010 Eighth International Conference on ICT and Knowledge Engineering.

[27]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[28]  Brahim Ouhbi,et al.  HCHIRSIMEX: An extended method for domain ontology learning based on conditional mutual information , 2014, 2014 Third IEEE International Colloquium in Information Science and Technology (CIST).

[29]  Brahim Ouhbi,et al.  Learning Non-taxonomic Relationships of Financial Ontology , 2015, KEOD.

[30]  Dan Klein,et al.  Learning Accurate, Compact, and Interpretable Tree Annotation , 2006, ACL.

[31]  Hua-Qiong Wang,et al.  Ontology-Based Medical Data Integration for Regional Healthcare Application , 2014 .

[32]  Syed Sibte Raza Abidi,et al.  A multi-phase correlation search framework for mining non-taxonomic relations from unstructured text , 2012, Knowledge and Information Systems.

[33]  Thomas R. Gruber,et al.  A translation approach to portable ontology specifications , 1993, Knowl. Acquis..

[34]  Lina Zhou,et al.  Improving financial data quality using ontologies , 2012, Decis. Support Syst..

[35]  Brahim Ouhbi,et al.  Building ontologies: A state of the art, and an application to Finance domain , 2014, 2014 International Conference on Next Generation Networks and Services (NGNS).

[36]  Masoud Makrehchi,et al.  Automatic Taxonomy Extraction Using Google and Term Dependency , 2007, IEEE/WIC/ACM International Conference on Web Intelligence (WI'07).

[37]  Yishi Zhang,et al.  Feature subset selection with cumulate conditional mutual information minimization , 2012, Expert Syst. Appl..

[38]  Oren Etzioni,et al.  Open Language Learning for Information Extraction , 2012, EMNLP.