Ten Challenges for Ontology Matching

An Ontological Approach to Knowledge Building by Data Integration

This paper discusses the uncertainty in the automation of knowledge building from heterogeneous raw datasets. Ontologies play a critical role in such a process by providing a well consolidated support to link and semantically integrate datasets via interoperability, as well as semantic enrichment and annotations. By adopting Semantic Web technology, the resulting ecosystem is fully machine consumable. However, while the manual alignment of concepts from different vocabularies is reasonable at a small scale, fully automatic mechanisms are required once the target system scales up, leading to a significant uncertainty.

Knowledge-oriented semantics modelling towards uncertainty reasoning

Distributed reasoning in M2M leverages the expressive power of ontology to enable semantic interoperability between heterogeneous systems of connected devices. Ontology, however, lacks the built-in, principled support to effectively handle the uncertainty inherent in M2M application domains. Thus, efficient reasoning can be achieved by integrating the inferential reasoning power of probabilistic representations with the first-order expressiveness of ontology. But there remains a gap with current probabilistic ontologies since state-of-the-art provides no compatible representation for simultaneous handling of discrete and continuous quantities in ontology. This requirement is paramount, especially in smart homes, where continuous quantities cannot be avoided, and simply mapping continuous information to discrete states through quantization can cause a great deal of information loss. In this paper, we propose a hybrid probabilistic ontology that can simultaneously handle distributions over discrete and continuous quantities in ontology. We call this new framework HyProb-Ontology, and it specifies distributions over properties of classes, which serve as templates for instances of classes to inherit as well as overwrite some aspects. Since there cannot be restriction on the dependency topology of models that HyProb-Ontology can induce across different domains, we can achieve a unified Ground Hybrid Probabilistic Model by conditional Gaussian fuzzification of the distributions of the continuous variables in ontology. From the results of our experiments, this unified model can achieve exact inference with better performance over classical Bayesian networks.

A novel ontology matching approach using key concepts

Purpose

– Ontologies are used to formally describe the concepts within a domain in a machine-understandable way. Matching of heterogeneous ontologies is often essential for many applications like semantic annotation, query answering or ontology integration. Some ontologies may include a large number of entities which make the ontology matching process very complex in terms of the search space and execution time requirements. The purpose of this paper is to present a technique for finding degree of similarity between ontologies that trims down the search space by eliminating the ontology concepts that have less likelihood of being matched.

Design/methodology/approach

– Algorithms are written for finding key concepts, concept matching and relationship matching. WordNet is used for solving synonym problems during the matching process. The technique is evaluated using the reference alignments between ontologies from ontology alignment evaluation initiative benchmark in terms of degree of similarity, Pearson’s correlation coefficient and IR measures precision, recall and F-measure.

Findings

– Positive correlation between the degree of similarity and degree of similarity (reference alignment) and computed values of precision, recall and F-measure showed that if only key concepts of ontologies are compared, a time and search space efficient ontology matching system can be developed.

Originality/value

– On the basis of the present novel approach for ontology matching, it is concluded that using key concepts for ontology matching gives comparable results in reduced time and space.

An overview of search strategies in distributed environments

Distributed systems are populated by a large number of heterogeneous entities that join and leave the systems dynamically. These entities act as clients and providers and interact with each other in order to get a resource or to achieve a goal. To facilitate the collaboration between entities, the system should provide mechanisms to manage the information about which entities or resources are available in the system at a certain moment, as well as how to locate them in an efficient way. However, this is not an easy task in open and dynamic environments where there are changes in the available resources and global information is not always available. In this paper, we present a comprehensive vision of search in distributed environments. This review not only considers the approaches of the peer-to-peer area, but also the approaches from three more areas: service-oriented environments, multi-agent systems, and complex networks. In these areas, the search for resources, services, or entities plays a key role for the proper performance of the systems built on them. The aim of this analysis is to compare approaches from these areas taking into account the underlying system structure and the algorithms or strategies that participate in the search process.

Cross-terminology mapping challenges: a demonstration using medication terminological systems

Standardized terminological systems for biomedical information have provided considerable benefits to biomedical applications and research. However, practical use of this information often requires mapping across terminological systems-a complex and time-consuming process. This paper demonstrates the complexity and challenges of mapping across terminological systems in the context of medication information. It provides a review of medication terminological systems and their linkages, then describes a case study in which we mapped proprietary medication codes from an electronic health record to SNOMED CT and the UMLS Metathesaurus. The goal was to create a polyhierarchical classification system for querying an i2b2 clinical data warehouse. We found that three methods were required to accurately map the majority of actively prescribed medications. Only 62.5% of source medication codes could be mapped automatically. The remaining codes were mapped using a combination of semi-automated string comparison with expert selection, and a completely manual approach. Compound drugs were especially difficult to map: only 7.5% could be mapped using the automatic method. General challenges to mapping across terminological systems include (1) the availability of up-to-date information to assess the suitability of a given terminological system for a particular use case, and to assess the quality and completeness of cross-terminology links; (2) the difficulty of correctly using complex, rapidly evolving, modern terminologies; (3) the time and effort required to complete and evaluate the mapping; (4) the need to address differences in granularity between the source and target terminologies; and (5) the need to continuously update the mapping as terminological systems evolve.