Semantic Web: – Interoperability,Usability,Applicability

Extracting information from Web pages for populating large, cross-domain knowledge bases requires methods which are suitable across domains, do not require manual effort to adapt to new domains, are able to deal with noise, and integrate information extracted from different Web pages. Recent approaches have used existing knowledge bases to learn to extract information with promising results, one of those approaches being distant supervision. Distant supervision is an unsupervised method which uses background information from the Linking Open Data cloud to automatically label sentences with relations to create training data for relation classifiers. In this paper we propose the use of distant supervision for relation extraction from the Web. Although the method is promising, existing approaches are still not suitable for Web extraction as they suffer from three main issues: data sparsity, noise and lexical ambiguity. Our approach reduces the impact of data sparsity by making entity recognition tools more robust across domains and extracting relations across sentence boundaries using unsupervised co-reference resolution methods. We reduce the noise caused by lexical ambiguity by employing statistical methods to strategically select training data. To combine information extracted from multiple sources for populating knowledge bases we present and evaluate several information integration strategies and show that those benefit immensely from additional relation mentions extracted using co-reference resolution, increasing precision by 8%. We further show that strategically selecting training data can increase precision by a further 3%.

Open information extraction approaches are useful but insufficient alone for populating the Web with machine readable information as their results are not directly linkable to, and immediately reusable from, other Linked Data sources. This work proposes a novel paradigm, named Open Knowledge Extraction, and its implementation (Legalo) that performs unsupervised, open domain, and abstractive knowledge extraction from text for producing machine readable information. The implemented method is based on the hypothesis that hyperlinks (either created by humans or knowledge extraction tools) provide a pragmatic trace of semantic relations between two entities, and that such semantic relations, their subjects and objects, can be revealed by processing their linguistic traces (i.e. the sentences that embed the hyperlinks) and formalised as Semantic Web triples and ontology axioms. Experimental evaluations conducted on validated text extracted from Wikipedia pages, with the help of crowdsourcing, confirm this hypothesis showing high performances. A demo is available at http://wit.istc.cnr.it/stlab-tools/legalo.

Crowdsourcing techniques provide effective means for solving a variety of ontology engineering problems. Yet, they are mainly used as external support to ontology engineering, without being closely integrated into the work of ontology engineers. In this paper we investigate how to closely integrate crowdsourcing into ontology engineering practices. Firstly, we show that a set of basic crowdsourcing tasks are used recurrently to solve a range of ontology engineering problems. Secondly, we present the uComp Protégé plugin that facilitates the integration of such typical crowdsourcing tasks into ontology engineering from within the Protégé ontology editor. An evaluation of the plugin in a typical ontology engineering scenario where ontologies are built from automatically learned semantic structures, shows that its use reduces the working times for the ontology engineers 11 times, lowers the overall task costs by 40% to 83% depending on the crowdsourcing settings used and leads to data quality comparable with that of tasks performed by ontology engineers. Evaluations on a large anatomy ontology confirm that crowdsourcing is a scalable and effective method: good quality results (accuracy of 89% and 99%) are obtained while achieving cost reductions of 75% from the ontology engineer costs and providing comparable overall task duration.

The Visual Notation for OWL Ontologies (VOWL) is a well-specified visual language for the user-oriented representation of ontologies. It defines graphical depictions for most elements of the Web Ontology Language (OWL) that are combined to a force-directed graph layout visualizing the ontology. In contrast to related work, VOWL aims for an intuitive and comprehensive representation that is also understandable to users less familiar with ontologies. This article presents VOWL in detail and describes its implementation in two different tools: ProtégéVOWL and WebVOWL. The first is a plugin for the ontology editor Protégé, the second a standalone web application. Both tools demonstrate the applicability of VOWL by means of various ontologies. In addition, the results of three user studies that evaluate the comprehensibility and usability of VOWL are summarized. They are complemented by findings from an interview with experienced ontology users and from testing the visual scope and completeness of VOWL with a benchmark ontology. The evaluations helped to improve VOWL and confirm that it produces comparatively intuitive and comprehensible ontology visualizations.

The formal representation of clinical knowledge is still an open research topic. Classical representation languages for clinical guidelines are used to produce diagnostic and treatment plans. However, they have important limitations, e.g. when looking for ways to re-use, combine, and reason over existing clinical knowledge. These limitations are especially problematic in the context of multimorbidity; patients that suffer from multiple diseases. To overcome these limitations, this paper proposes a model for clinical guidelines (TMR4I) that allows the re-use and combination of knowledge from multiple guidelines. Semantic Web technology is applied to implement the model, allowing us to automatically infer interactions between recommendations, such as recommending the same drug more than once. It relies on an existing Linked Data set, DrugBank, for identifying drug-drug interactions. We evaluate the model by applying it to two realistic case studies on multimorbidity that combine guidelines for two (Duodenal Ulcer and Transient Ischemic Attack) and three diseases (Osteoarthritis, Hypertension and Diabetes) and compare the results with existing methods.

With the recent growth of Linked Data on the Web there is an increased need for knowledge engineers to find ontologies to describe their data. Only limited work exists that addresses the problem of searching and ranking ontologies based on a given query term. In this paper we introduce DWRank, a two-staged bi-directional graph walk ranking algorithm for concepts in ontologies. DWRank characterises two features of a concept in an ontology to determine its rank in a corpus, the centrality of the concept to the ontology within which it is defined (HubScore) and the authoritativeness of the ontology in which it is defined (AuthorityScore). DWRank then uses a Learning to Rank approach to learn the feature weights for the two aforementioned ranking strategies. We compare DWRank with state-of-the-art ontology ranking models and traditional information retrieval algorithms. This evaluation shows that DWRank significantly outperforms the best ranking models on a benchmark ontology collection for the majority of the sample queries defined in the benchmark. In addition, we compare the effectiveness of the HubScore part of our algorithm with the state-of-the-art ranking model to determine a concept centrality and show the improved performance of DWRank in this aspect. Finally, we evaluate the effectiveness of the design decisions made for the AuthorityScore method in DWRank to find missing inter-ontology links and present a graph-based analysis of the ontology corpus that shows the increased connectivity of the ontology corpus after extraction of the implicit inter-ontology links.

Using a pay-as-you-go strategy, we allow for a community of users to validate or invalidate mappings obtained by an automatic ontology matching system using consensus for each mapping. The ultimate objectives are effectiveness – improving the quality of the obtained alignment (set of mappings) measured in terms of F-measure as a function of the number of user interactions – and robustness – making the system as much as possible impervious to user validation errors. Our strategy consists of two major steps: candidate mapping selection, which ranks mappings based on their perceived quality so that users are presented first with those mappings with lowest quality, and feedback propagation, which seeks to validate or invalidate those mappings that are perceived to be similar to the mappings already presented to the users for validation. The purpose of these two strategies is twofold: achieve greater improvements earlier and minimize overall user interaction. There are three important features of our approach: the use of a dynamic ranking mechanism to adapt to the new conditions after each user interaction, the presentation of each mapping for validation more than once – revalidation – because of possible user errors, and the immediate propagation of the user input on a mapping without first achieving consensus for that mapping. We study extensively the effectiveness and robustness of our approach as several of these parameters change, namely the error and revalidation rates, as a function of the number of iterations, to provide conclusive guidelines for the design and implementation of multi-user feedback ontology matching systems.