ArticlePDF Available

Towards a Multi-level Upper Ontology/ foundation Ontology Framework as Background Knowledge for Ontology Matching Problem

Authors:
Alok Chauhan at VIT University, Chennai Campus
Alok Chauhan
  • VIT University, Chennai Campus
Vijayakumar Varadarajan
Vijayakumar Varadarajan
Ramesh Ragala
Ramesh Ragala
Ramesh Ragala
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Download full-text PDF
Read full-text
Download citation

Abstract and Figures

This paper emphasizes on application of background knowledge in ontology matching problems. The main idea is to have a multi-level structure of ontologies (higher the level, more universal/general the ontology is) to be used as background knowledge for ontology matching. This requires next generation of new upper level ontologies, which are at higher level than current set of upper level ontologies. To create such higher level ontologies, usage of new/ alternative philosophical models is suggested.
Figures - uploaded by Alok Chauhan
Author content
All figure content in this area was uploaded by Alok Chauhan
Content may be subject to copyright.
Content uploaded by Alok Chauhan
Author content
All content in this area was uploaded by Alok Chauhan on Jun 12, 2015
Content may be subject to copyright.
Procedia Computer Science 50 ( 2015 ) 631 – 634
Available online at www.sciencedirect.com
1877-0509 © 2015 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license
(http://creativecommons.org/licenses/by-nc-nd/4.0/).
Peer-review under responsibility of scientific committee of 2nd International Symposium on Big Data and Cloud Computing (ISBCC’15)
doi: 10.1016/j.procs.2015.04.096
ScienceDirect
2nd International Symposium on Big Data and Cloud Computing (ISBCC’15)
Towards a multi-level upper ontology/ foundation ontology framework as background knowledge for
ontology matching problem
Alok Chauhana
*
, V Vijayakumarb, Ramesh Ragalac
a SCSE, VIT University, Chennai-600127, Tamil Nadu, India
b SCSE, VIT University, Chennai-600127, Tamil Nadu, India
c SCSE, VIT University, Chennai-600127, Tamil Nadu,India
Abstract
This paper emphasizes on application of background knowledge in ontology matching problems. The main idea is to
have a multi-level structure of ontologies (higher the level, more universal/general the ontology is) to be used as
background knowledge for ontology matching. This requires next generation of new upper level ontologies, which
are at higher level than current set of upper level ontologies. To create such higher level ontologies, usage of new/
alternative philosophical models is suggested.
© 2015 The Authors. Published by Elsevier B.V.
Peer-review under responsibility of scientific committee of 2nd International Symposium on Big Data and Cloud Computing
(ISBCC’15).
Keywords: Upper ontology; ontology matching; multi-level structure
1. Introduction
An ontology typically provides a vocabulary that describes a domain of interest and a specification of the meaning
of terms used in the vocabulary [1]. Semantic heterogeneity is biggest challenge in semantic web. Ontology
matching is a solution to the semantic heterogeneity problem. It finds correspondences between semantically related
entities of ontologies. These correspondences can be used for various tasks, such as ontology merging, query
* Corresponding author. Tel.: +91 44 3993 1099; fax: +91 44 3993 2555.
E-mail address: alok.chauha n@vit.a c.in
© 2015 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license
(http://creativecommons.org/licenses/by-nc-nd/4.0/).
Peer-review under responsibility of scientific committee of 2nd International Symposium on Big Data and Cloud Computing
(ISBCC’15)
632 Alok Chauhan et al. / Procedia Computer Science 50 ( 2015 ) 631 – 634
answering, or data translation [1]. It has been stated that the lack of background, most often domain specific
knowledge, is one of the key problems of matching systems these days [2].
2. Related Work
Viviana Mascardi, et al, have proposed set of algorithms that use upper ontologies as background knowledge.
They used upper ontologies such as DOLCE, SUMO-OWL and OpenCyc. It was found that these methods provide
better precision and F-measure as compared to direct methods (which don’t match via background knowledge)[3].
Domain-aware ontology matching also shows promising results when compared with standard approaches. It has
been found that boot-strapping the matching process with domain knowledge is advantageous [4].
Ontology matching via harvesting semantic web gives encouraging results and is particularly important from the
viewpoint of scaling up the matching process [5]. Automatic selection of background knowledge is another
approach which enriches ontology matching process with information retrieval techniques [6]. Upper ontologies in
conjunction with word sense disambiguation techniques are found to be useful in repairing incorrect
correspondences found in ontology matching process [7].
A more generic framework known as context-based matching has been proposed recently and it shows that
limitations of content-based matching can be taken care of by it [8]. Automating the process of discovering missing
background knowledge in ontology matching could be helpful in this regard and emphasizes the importance of focus
area being discussed about [9].
Solutions provided for contextual ontology alignment of Linked Open Data with an upper ontology addresses
important issues related with schema-level mappings [10]. Background ontology is shown to be very helpful in
matching unstructured vocabularies and this paper extends this idea further [11].
3. Proposed System
A multi-level structure in the form of a tree of upper ontologies is proposed as a background knowledge
framework for the purpose of matching ontologies. As shown in Fig. 1, the whole matching process can be thought
of as consisting of following three phases:
Phase I: Semantic entities from source and target ontologies are anchored to leaf upper ontologies of background
knowledge framework in first scan. Any string based anchoring mechanism can be used for this purpose.
Phase II: In the second scan of the tree of upper ontologies, lowest common subsumer upper ontology is found
on the basis of Tarjan’s lowest common ancestor/subsumer algorithm (Fig. 2).
Phase III: Semantic relationship is established between entities of Phase I by again applying algorithm
mentioned in Phase II to lowest common subsume ontology found in Phase II.
633
Alok Chauhan et al. / Procedia Computer Science 50 ( 2015 ) 631 – 634
Fig. 1 A multi-level background knowledge framework
634 Alok Chauhan et al. / Procedia Computer Science 50 ( 2015 ) 631 – 634
Fig. 2
4. Conclusion & future work
Proposed framework is a comprehensive solution to ontology matching problem based on matching via
background knowledge paradigm. It does assume the existence of higher level upper ontologies, for which usage of
new alternative philosophical model such as Madhyastha-darshan [12] would be explored in future work.
Experimental verification of the proposed model will also be carried out and results of proposed matching system
will be compared with existing state-of-the-art models.
References
1. P. Shvaiko, J . Euz enat: Ontology matching: state of the art and future challenges IEEE Transactions on Knowledge and Data Engineering,
2013.
2. C. Kingkaew: Using Unstruc tured D ocume nts as Background Knowledg e for O ntology Matching In Proceedings of IMLCS, 2012.
3. V. Mascardi, A. Locoro, P. Rosso: Automatic Ontology Matching Via Upper Ontologies: A Systematic Evaluation TKDE, 2009.
4. K. Slabbekoorn, L. Hollink, G. Houben: Domain-aware Ontology Matching In Proceedings of ISWC, 2012.
5. M. Sabou, M. d'Aquin, and E. Motta: Exploring the Semantic Web as Background Knowledge for Ontology Matching Journal on Data
Semantics, 2008.
6. C. Quix, P. Roy, D. Kensche: Automatic Selection of Background Knowledge for Ontology Matching In Proceedings of SWIM, 2011.
7. A. Locoro, V. Mascardi: A correspondence repair algorithm based onword sense disambiguation and upper ontologies In Proceedings of
KEOD, 2009.
8. A. Locoro, J. David, J. Euzenat: Context-based matching: design of a flexible framework and experiment JoDS, 2014.
9. F. Giun chiglia and P. Shvaiko a nd M. Ya tskevich: D iscove ring Mi ssing Ba ckground Knowledge i n Ontology Ma tchin g In Proceedings of
ECAI, 2006.
10. P. Jain, P. Z. Yeh, K. Verma, R. G. Vasquez, M. Damova, P. Hitzler, Amit P. Sheth: Contextual Ontology Alignment of LOD with an Upper
Ontology: A Case Study with Proton In Proceedings of ESWC, 2011.
11. Z. Aleksovski, M. Klein, W. ten Kate, F. van Harmelen: Matching Unstructured Vocabularie s using a Back ground Ontolo gy In Proceedings
of EKAW, 2006.
12. http://madhyasth-darshan.in fo/
_______________________________
Algorithm Lowest Common Subsumer
1. ALGORITHM LCS (UOi, UOj, T)
2. // INPUT: UOi and UOj are the two Upper Ontologies in Tree T where
i ≠j and
{a1, a2, a3, … ak} ϵ OUi ,where 1 <i ≤n.
3. // OUTPUT: Lowest Common Subsumer Ontology
4. BEGIN
5. u Å
Å UOi, v ÅÅ UOj;
6. while(T.depth(u) > T.depth(v)) do
7. u ÅÅ parent(u);
8. while(T.depth(v) > T.depth(u)) do
9. v ÅÅ parent(v);
10. while(u ≠ v) do
11. u ÅÅ parent(u);
12. v ÅÅ parent(v);
13. return(LCS(ai, aj, u)); // ai, aj ϵ u
14. END
... There, the key point is the relationship between the ontology of services and universal ontology. Along with two-level ontologies, multilevel ones are also considered in diverse variants of level selection [1,12]. ...
... In [1,2,11,12], conceptual directions for the creation and development of applied ontologies and families of ontologies are proposed for various subsequent implementations. To automatize these processes, further formalization is needed: the development and study of appropriate formal models. ...
Ontological support formation for constructive-synthesizing modeling of information systems development processes
Article
Full-text available
  • Oct 2018
The globalization of information systems (ISs) in the process of continuous operation and modernization creates new problems and reveals specific representations of IS tasks. Such a complex industry IS, requiring appropriate ontological support, is the unified automated system for managing freight traffic of Ukrzaliznytsia (ACS FT UZ-U). To develop the infrastructure information subsystems such as rolling stock and traction staff, traffic management, finance, personnel and a number of others, it is necessary to develop interconnected ontological support. Therefore, methods and means of ontological support of constructive-synthesizing modeling (OCSM) have been developed, designed to support the processes of multistage creation, a long period of operation and the continuous development of the ACS FT UZ-U. The results obtained are distinguished by universalism, as they provide opportunities for representing the evolution of the object (IS) and the content of ontologies in the OCSM. The formation of models and methods of the OCSM has been obtained by expanding relations and mappings as well as by creating new generating structures, complementing classes of signatures with new constructive relations. At the same time, the model of a unified, universal and customizable ontological constructive structure (OCS) has been developed. The OCS takes into account the requirements for representing the processes of expanding the subject area as well as unifying knowledge. For CSM problems, methods and means of modeling the conceptualization processes of developing objects have been created and constructive calculus has been devised for the generating class of mappings along with methods for constructing higher-order ontological objects. For the ontological support of the CSM processes in the context of expanding subject areas, the inference methods in the model of the OCSM constructive structure have been improved and procedures for meaningful, structural and related deducibility have been proposed together with multilevel inference methods. Examples have been given of the implementation of the currently existing procedures for creating new applications of the automated system ACS FT UZ-U using the proposed CSM tools. The examples demonstrate the adequacy of the developed models and means of the OCSM for the implementation of procedures for the development and maintenance of complex railway ACSs.
View
...  Merging Different Domain Knowledge Bases: Different domains have different knowledge base formats, which usually come in the form of different domain ontologies. In order to achieve semantic interoperability between various domain ontologies, the resource model implementation should consider merging them under a top‐level or upper ontology [24] ...
... ‚ Merging Different Domain Knowledge Bases: Different domains have different knowledge base formats, which usually come in the form of different domain ontologies. In order to achieve semantic interoperability between various domain ontologies, the resource model implementation should consider merging them under a top-level or upper ontology [24] for cross-domain synthesis of the resources in Smart Grid. ...
An Event-Based Resource Management Framework for Distributed Decision-Making in Decentralized Virtual Power Plants
Article
Full-text available
  • Jul 2016
The Smart Grid incorporates advanced information and communication technologies (ICTs) in power systems, and is characterized by high penetration of distributed energy resources (DERs). Whether it is the nation-wide power grid or a single residential building, the energy management involves different types of resources that often depend on and influence each other. The concept of virtual power plant (VPP) has been proposed to represent the aggregation of energy resources in the electricity market, and distributed decision-making (DDM) plays a vital role in VPP due to its complex nature. This paper proposes a framework for managing different resource types of relevance to energy management for decentralized VPP. The framework views VPP as a hierarchical structure and abstracts energy consumption/generation as contractual resources, i.e., contractual offerings to curtail load/supply energy, from third party VPP participants for DDM. The proposed resource models, event-based approach to decision making, multi-agent system and ontology implementation of the framework are presented in detail. The effectiveness of the proposed framework is then demonstrated through an application to a simulated campus VPP with real building energy data.
View
... Based on the literature it is noted, that only a specific ontology categories are part of the analysis and specification of requirements [20] e.g.: application domain [21], application domain feature model [22], system behavior ontologies [23]. Meanwhile in software production many other categories of ontologies are distinguished, i.e. upper ontology [24], software process ontology [25], requirements ontology [26], software architecture ontology [27], and many others. The point of view adopted in the article distinguishes between methods and accompanying tools. ...
Reconciling the Expectations of Ontology Engineering to the Process of Requirements Elicitation
Conference Paper
Full-text available
  • Sep 2019
The paper is devoted to research into methods for requirements elicita-tion. From our perspective, the use of ontology engineering is particularly interesting. The author focuses his attention on selected aspects of ontology engineering , resulting from the needs of his doctoral thesis, organized by the Design Science Research paradigm. The article seeks to recognize a certain level of interplay between ontology engineering and individual tasks of the process of requirements elicitation (a synergy). Therefore, it aims to explain possible expectations for ontology engineering, which result from the specific features of the process of requirements elicitation. In order to identify the guidelines for the developing domain ontologies based on the requirements elicitation process. The originality of the article results from the consideration of the interplay between ontology engineering and requirements engineering, relative to the context of software engineering. As a result, the software engineering layers propagated by Pressman have been extended to include another layer of management philosophy. The rationale behind this was the noticing of the impact of other concepts of philosophy on this work, such as axiology or epistemology.
View
... Above model represents a holistic/universal view of meaning in terms of existing constructs, though at present we do not have any methodology to support this model but an effort in this direction has been made by the authors [8] and process to propose a new foundation ontology is underway. ...
Ontology Matching Techniques: A Gold Standard Model
Preprint
Full-text available
  • Nov 2018
Typically an ontology matching technique is a combination of much different type of matchers operating at various abstraction levels such as structure, semantic, syntax, instance etc. An ontology matching technique which employs matchers at all possible abstraction levels is expected to give, in general, best results in terms of precision, recall and F-measure due to improvement in matching opportunities and if we discount efficiency issues which may improve with better computing resources such as parallel processing. A gold standard ontology matching model is derived from a model classification of ontology matching techniques. A suitable metric is also defined based on gold standard ontology matching model. A review of various ontology matching techniques specified in recent research papers in the area was undertaken to categorize an ontology matching technique as per newly proposed gold standard model and a metric value for the whole group was computed. The results of the above study support proposed gold standard ontology matching model.
View
... An upper ontology is a top-level ontology which contains surface level information (Chauhan, Vijayakumar, & Ragala, 2015). ...
Open-ended self-reflection based personality trait assessment: A Lexical based upper ontological approach with fact clusters
Conference Paper
  • Oct 2018
Personal trait analysis is a key ingredient which can be used to personalize psychotherapy sessions. Self-reflection could be identified as a vital input which could be used for personal trait assessment. Although, there are no computerized trait assessment mechanisms implemented which could accept, open-ended self-reflection as the input. Computational applications in personal trait assessments have not gone beyond closed-ended MCQ based questionnaires. This research proposes a lexicon based ontological structure mapped with contextually defined fact clusters for open-ended self-reflection based personality trait assessment. This application will aide to enhance the therapeutic alliance between consultant and patients leading into satisfactory therapy outcomes.
View
Using Background Knowledge to Enhance Biomedical Ontology Matching
Thesis
Full-text available
  • Oct 2018
Life sciences produce a huge amount of data (e.g., clinical trials, scientific articles) so that integrating and analyzing all the datasets related to a given research question like the correlation between phenotypes and genotypes, is a key element for knowledge discovery. The life sciences community adopted Semantic Web technologies to achieve data integration and interoperability, especially ontologies which are the key technology to represent and share the increasing amount of data on the Web. Indeed, ontologies provide a common domain vocabulary for humans, and formal entity definitions for machines.A large number of biomedical ontologies and terminologies has been developed to represent and annotate various datasets. However, datasets represented with different overlapping ontologies are not interoperable. It is therefore crucial to establish correspondences between the ontologies used; an active area of research known as ontology matching.Original ontology matching methods usually exploit the lexical and structural content of the ontologies to align. These methods are less effective when the ontologies to align are lexically heterogeneous i.e., when equivalent concepts are described with different labels. To overcome this issue, the ontology matching community has turned to the use of external knowledge resources as a semantic bridge between the ontologies to align. This approach arises several new issues mainly: (1) the selection of these background resources, (2) the exploitation of the selected resources to enhance the matching results. Several works have dealt with these issues jointly or separately. In our thesis, we made a systematic review and historical evaluation comparison of state-of-the-art approaches.Ontologies, others than the ones to align, are the most used background knowledge resources. Related works often select a set of complete ontologies as background knowledge, even if, only fragments of the selected ontologies are actually effective for discovering new mappings. We propose a novel BK-based ontology matching approach that selects and builds a knowledge resource with just the right concepts chosen from a set of ontologies. The conducted experiments showed that our BK selection approach improves efficiency without loss of effectiveness.Exploiting background knowledge resources in ontology matching is a double-edged sword: while it may increase recall (i.e., retrieve more correct mappings), it may lower precision (i.e., produce more incorrect mappings). We propose two methods to select the most relevant mappings from the candidate ones: (1) based on a set of rules and (2) with Supervised Machine Learning. We experiment and evaluate our approach in the biomedical domain, thanks to the profusion of knowledge resources in biomedicine (ontologies, terminologies and existing alignments).We evaluated our approach with extensive experiments on two Ontology Alignment Evaluation Initiative (OAEI) benchmarks. Our results confirm the effectiveness and efficiency of our approach and overcome or compete with state-of-the-art matchers exploiting background knowledge resources.
View
OntoApp : une approche déclarative pour la simulation du fonctionnement d’un logiciel dès une étape précoce du cycle de vie de développement
Thesis
  • Sep 2017
Dans cette thèse, nous étudions plusieurs modèles de collaboration entre l’ingénierie logiciel et le web sémantique. À partir de l’état de l’art, nous proposons une approche d’utilisation de l’ontologie dans la couche de métier d’une application. L’objectif principal de notre travail est de fournir au développeur des outils pour concevoir la matière déclarative une couche de métier "exécutable" d’une application afin de simuler son fonctionnement et de montrer ainsi la conformité de l’application par rapport aux exigences du client au début du cycle de vie du logiciel. Un autre avantage de cette approche est de permettre au développeur de partager et de réutiliser la description de la couche de métier d’une application dans un domaine en utilisant l’ontologie. Celle-ci est appelée "patron d’application". La réutilisation de la description de la couche de métier d’une application est un aspect intéressant à l'ingénier logiciel. C’est le point-clé que nous voulons considérer dans cette thèse. Dans la première partie de notre travail, nous traitons la modélisation de la couche de métier. Nous présentons d’abord une approche fondée sur l’ontologie pour représenter les processus de métiers et les règles de métiers et nous montrons comment vérifier la cohérence du processus et de l’ensemble des règles de métier. Puis, nous présentons le mécanisme de vérification automatique de la conformité d’un processus de métier avec un ensemble de règles de métier. La deuxième partie de cette thèse est consacrée à définir une méthodologie, dite de personnalisation, de création une application à partir d'un "patron d’application". Cette méthode permettra à l'utilisateur d'utiliser un patron d'application pour créer sa propre application en évitant les erreurs de structures et les erreurs sémantiques. Nous introduisons à la fin de cette partie, la description d’une plateforme expérimentale permettant d’illustrer la faisabilité des mécanismes proposés dans cette thèse. Cette plateforme est réalisée sur un SGBD relationnel.
View
Ontologies for Software Engineering: Past, Present and Future
Article
Full-text available
  • Mar 2016
Background/Objectives: Research in recent years has probed integration amongst research field of Software Engineering and Semantic Web technology, addressing the advantages of applying Semantic techniques to the field of Software Engineering. Prolifically published studies have further substantiated the benefits of ontologies to the field of Software Engineering, which clearly motivate us to explore further opportunities available in this collaborated field. This paper is a survey expounding such opportunities while discussing the role of ontologies as a Software Life-Cycle support technology. Method/Statistical Analysis: Survey centred on providing an overview of the state-of-art of all the ontologies available for Software Engineering followed by their categorization based on software life cycle phases and their application scope. Findings: Characterization of ontologies as a Software Life-cycle support technology, instigated by the increasing need to investigate the interplay between Semantic Web & Software Engineering with the ultimate goal of enabling & improving Software Engineering capabilities. Application/Improvements: This paper discusses the practical and potential applications of ontologies in the field of Software Engineering followed by the issues and challenges that will keep this field dynamic and lively for years to come.
View
P-J Matching Model of Knowledge Workers
Article
Full-text available
  • Dec 2015
This article develops a decision analysis method that optimizes the knowledge worker-position match considering various characteristics of knowledge workers. First, we construct hierarchy evaluation index systems that match the knowledge worker with the right position. Second, we transform the multiple indicator linguistic assessment information of knowledge workers and positions into the form of triangular fuzzy numbers, compute and analyze the fuzzy numbers based on the extension principle of fuzzy numbers, and then construct multi-objective optimization model containing fuzzy numbers. Third, we use the membership function method of fuzzy number in order to transform and solve the model. Lastly, samples are collected in an iron and steel organization. Results indicate the feasibility and effectiveness of the method.
View
Contextual Ontology Alignment of LOD with an Upper Ontology: A Case Study with Proton
Conference Paper
Full-text available
  • Jul 2011
  • Lect Notes Comput Sci
The Linked Open Data (LOD) is a major milestone towards realizing the Semantic Web vision, and can enable applications such as robust Question Answering (QA) systems that can answer queries requiring multiple, disparate information sources. However, realizing these applications requires relationships at both the schema and instance level, but currently the LOD only provides relationships for the latter. To address this limitation, we present a solution for automatically finding schema-level links between two LOD ontologies – in the sense of ontology alignment. Our solution, called BLOOMS+, extends our previous solution (i.e. BLOOMS) in two significant ways. BLOOMS+ 1) uses a more sophisticated metric to determine which classes between two ontologies to align, and 2) considers contextual information to further support (or reject) an alignment. We present a comprehensive evaluation of our solution using schema-level mappings from LOD ontologies to Proton (an upper level ontology) – created manually by human experts for a real world application called FactForge. We show that our solution performed well on this task. We also show that our solution significantly outperformed existing ontology alignment solutions (including our previously published work on BLOOMS) on this same task.
View
Using Unstructured Documents as Background Knowledge for Ontology Matching
Conference Paper
Full-text available
  • Aug 2012
Ontology Matching is the process of finding correspondences between two given ontologies. Many traditional matching techniques have been proposed and the majority of approaches rely on lexical and structural matching techniques which need a sufficient lexical overlap and a rich structure. There is a new approach using background knowledge for ontology matching. This method provides a way to find matches missed by the other approaches. There are various approaches using background knowledge, but most of them require that the background knowledge is explicitly given as input to the matching process. However, the background knowledge has to be provided as a formal ontology which is often not available. Our work extends this approach by considering unstructured documents as background knowledge. We evaluate our matcher with the sample data set from the conference track of the Ontology Alignment Evaluation Initiative (OAEI) campaign. We use precision, recall and f-measure as our metric for evaluating the results. The evaluation shows that our matcher overcomes the traditional matching techniques in every case.
View
Automatic selection of background knowledge for ontology matching
Article
Full-text available
  • Jun 2011
Background knowledge in form of ontologies is an important source of information for many tasks in the semantic web, e.g., ontology matching, ontology construction and editing, natural language processing. In particular, ontology matching and integration can benefit from background ontologies as semantic relationships may be discovered which cannot be identified otherwise. In existing approaches, the background ontology has to be provided often by the user. Therefore, we present an approach that uses background knowledge for matching; but in contrast to other approaches, our approach is able to identify appropriate background ontologies automatically. We implemented this approach in our matching frame-work GeRoMeSuite and tested it with several data sets from the Ontology Alignment Evaluation Initiative (OAEI) campaign. The evaluation shows that the use of background knowledge improves the result in most cases and that our ontology discovery process is able to find appropriate background knowledge to bridge the gap between the two input ontologies.
View
Matching Unstructured Vocabularies Using a Background Ontology
Conference Paper
Full-text available
  • Oct 2006
  • Lect Notes Comput Sci
Existing ontology matching algorithms use a combination of lexical and structural correspondance between source and target ontologies. We present a realistic case-study where both types of overlap are low: matching two unstruc- tured lists of vocabulary used to describe patients at Intensive Care Units in two different hospitals. We show that indeed existing matchers fail on our data. We then discuss the use of background knowledge in ontology matching problems. In particular, we discuss the case where the source and the target ontology are of poor semantics, such as flat lists, and where the background knowledge is of rich semantics, providing extensive descriptions of the properties of the concepts involved. We evaluate our results against a Gold Standard set of matches that we obtained from human experts.
View
A Correspondence Repair Algorithm based on Word Sense Disambiguation and Upper Ontologies.
Conference Paper
Full-text available
  • Jan 2009
In an ideal world, an ontology matching algorithm should return all the correct correspondences (it should be complete) and should return no wrong correspondences (it should be correct). In the real world, no imple- mented ontology matching algorithm is both correct and complete. For this reason, repairing wrong corre- spondences in an ontology alignment is a very pressing need to obtain more accurate alignments. This paper discusses an automatic correspondence repair method that exploits both upper ontologies to provide infor- mative context to concepts c2 o and c02 o0 belonging to an alignment a, and a context-based word sense disambiguation algorithm to assign c and c0 their correct meaning. This meaning is used to decide whether c and c0 are related, and to either keep or discard the correspondence < c; c0 >2 a, namely, to repair a. The experiments carried on are presented and the obtained results are provided. The advantages of the approach we propose are confirmed by a total average gain of 11,5% in precision for the alignments repaired against a 2% total average error.
View
Automatic Ontology Matching via Upper Ontologies: A Systematic Evaluation
Article
Full-text available
  • May 2010
Ontology matching" is the process of finding correspondences between entities belonging to different ontologies. This paper describes a set of algorithms that exploit upper ontologies as semantic bridges in the ontology matching process and presents a systematic analysis of the relationships among features of matched ontologies (number of simple and composite concepts, stems, concepts at the top level, common English suffixes and prefixes, ontology depth), matching algorithms, used upper ontologies, and experiment results. This analysis allowed us to state under which circumstances the exploitation of upper ontologies gives significant advantages with respect to traditional approaches that do no use them. We run experiments with SUMO-OWL (a restricted version of SUMO), OpenCyc and DOLCE. The experiments demonstrate that when our "structural matching method via upper ontology" uses an upper ontology large enough (OpenCyc, SUMO-OWL), the recall is significantly improved while preserving the precision obtained without upper ontologies. Instead, our "non structural matching method" via OpenCyc and SUMO-OWL improves the precision and maintains the recall. The "mixed method" that combines the results of structural alignment without using upper ontologies and structural alignment via upper ontologies improves the recall and maintains the F-measure independently of the used upper ontology.
View
Using the semantic web as background knowledge for ontology mapping
Article
Full-text available
  • Jan 2006
While current approaches to ontology mapping produce good results by mainly relying on label and structure based similarity measures, there are several cases in which they fail to discover important mappings. In this paper we describe a novel approach to ontology mapping, which is able to avoid this limitation by using background knowledge. Existing approaches relying on background knowledge typically have one or both of two key limitations: 1) they rely on a manually selected reference ontology; 2) they suffer from the noise introduced by the use of semi-structured sources, such as text corpora. Our technique circumvents these limitations by exploiting the increasing amount of semantic resources available online. As a result, there is no need either for a manually selected reference ontology (the relevant ontologies are dynamically selected from an online ontology repository), or for transforming background knowledge in an ontological form. The promising results from experiments on two real life thesauri indicate both that our approach has a high precision and also that it can find mappings, which are typically missed by existing approaches.
View
Domain-Aware Ontology Matching
Conference Paper
  • Nov 2012
  • Lect Notes Comput Sci
The inherent heterogeneity of datasets on the Semantic Web has created a need to interlink them, and several tools have emerged that automate this task. In this paper we are interested in what happens if we enrich these matching tools with knowledge of the domain of the ontologies. We explore how to express the notion of a domain in terms usable for an ontology matching tool, and we examine various methods to decide what constitutes the domain of a given dataset. We show how we can use this in a matching tool, and study the effect of domain knowledge on the quality of the alignment. We perform evaluations for two scenarios: Last.fm artists and UMLS medical terms. To quantify the added value of domain knowledge, we compare our domain-aware matching approach to a standard approach based on a manually created reference alignment. The results indicate that the proposed domain-aware approach indeed outperforms the standard approach, with a large effect on ambiguous concepts but a much smaller effect on unambiguous concepts.
View
Ontology Matching: State of the Art and Future Challenges
Article
  • Jan 2013
After years of research on ontology matching, it is reasonable to consider several questions: is the field of ontology matching still making progress? Is this progress significant enough to pursue further research? If so, what are the particularly promising directions? To answer these questions, we review the state of the art of ontology matching and analyze the results of recent ontology matching evaluations. These results show a measurable improvement in the field, the speed of which is albeit slowing down. We conjecture that significant improvements can be obtained only by addressing important challenges for ontology matching. We present such challenges with insights on how to approach them, thereby aiming to direct research into the most promising tracks and to facilitate the progress of the field.
View
Context-Based Matching: Design of a Flexible Framework and Experiment
Article
  • Mar 2014
Context-based matching finds correspondences between entities from two ontologies by relating them to other resources. A general view of context-based matching is designed by analysing existing such matchers. This view is instantiated in a path-driven approach that (a) anchors the ontologies to external ontologies, (b) finds sequences of entities (path) that relate entities to match within and across these resources, and (c) uses algebras of relations for combining the relations obtained along these paths. Parameters governing such a system are identified and made explicit. They are used to conduct experiments with different parameter configurations to assess their influence. In particular, experiments confirm that restricting the set of ontologies reduces the time taken at the expense of recall and F-measure. Increasing path length within ontologies increases recall and F-measure as well. In addition, algebras of relations allow for a finer analysis, which shows that increasing path length provides more correct or non precise correspondences, but marginally increases incorrect correspondences.
View