Viktor de Boer

MultimediaN e-culture demonstrator

The main objective of the MultimediaN E-Culture project is to demonstrate how novel semantic-web and presentation technologies can be deployed to provide better indexing and search support within large virtual collections of cultural-heritage resources. The architecture is fully based on open web standards, in particular XML, SVG, RDF/OWL and SPARQL. One basic hypothesis underlying this work is that the use of explicit background knowledge in the form of ontologies/vocabularies/thesauri is in particular useful in information retrieval in knowledge-rich domains.

A redundancy-based method for the extraction of relation instances from the Web

The Semantic Web requires automatic ontology population methods. We developed an approach, that given existing ontologies, extracts instances of ontology relations, a specific subtask of ontology population. We use generic, domain-independent techniques to extract candidate relation instances from the Web and exploit the redundancy of information on the Web to compensate for loss of precision caused by the use of these generic methods. The candidate relation instances are then ranked based on co-occurrence with a small seed set. In an experiment, we extracted instances of the relation between artists and art styles. The results were manually evaluated against selected art resources. The method was also tested in the football domain. We also compare the performance of our ranking to that of a Google-hit count-based method.

Extracting instances of relations from web documents using redundancy

In this document we describe our approach to a specific subtask of ontology population, the extraction of instances of relations. We present a generic approach with which we are able to extract information from documents on the web. The method exploits redundancy of information to compensate for loss of precision caused by the use of domain independent extraction methods. In this paper, we present the general approach and describe our implementation for a specific relation instance extraction task in the art domain. For this task, we describe experiments, discuss evaluation measures and present the results.

Web Page Classification Using Image Analysis Features

Classification of web pages is usually done by extracting the textual content of the page and/or by extracting structural features from the HTML. In this work, we present a different approach, where we use the visual appearance of web pages for their classification.We extract generic, low-level visual features directly from the page as it is rendered by a web browser. The visual features used in this document are simple color and edge histograms, Gabor and texture features. These were extracted using an off-the-shelf visual feature extraction method. In three experiments, we classify web pages based on their aesthetic value, their recency and the type of website. Results show that these simple, global visual features already produce good classification results. We also introduce an online tool that uses the trained classifiers to assess new web pages.

Relation instantiation for ontology population using the web

The Semantic Web requires automatic ontology population methods. We developed an approach, that given existing ontologies, extracts instances of ontology relations, a specific subtask of ontology population. We use generic, domain independent techniques to extract candidate relation instances from the Web and exploit the redundancy of information on the Web to compensate for loss of precision caused by the use of these generic methods. The candidate relation instances are then ranked based on co-occurrence with a seed set. In an experiment, we extracted instances of the relation between artists and art styles. The results were manually evaluated against selected art resources.

SiteGuide: A tool for web site authoring support

We present ‘SiteGuide’, a tool that helps web designers to decide which information will be included in a new web site and how the information will be organized. SiteGuide takes as input URLs of web sites from the same domain as the site the user wants to create. It automatically searches the pages of these example sites for common topics and common structural features. On the basis of these commonalities it creates a model of the example sites. The model can serve as a starting point for the new web site. Also, it can be used to check whether important elements are missing in a concept version of the new site. Evaluation shows that SiteGuide is able to detect a large part of the common topics in example sites and to present these topics in an understandable form to its users. First results of a user study indicate that Siteguide helps users to create web site designs with better structured contents and links.

Clustering objects from multiple collections

Clustering methods cluster objects on the basis of a similarity measure between the objects. In clustering tasks where the objects come from more than one collection often part of the similarity results from features that are related to the collections rather than features that are relevant for the clustering task. For example, when clustering pages from various web sites by topic, pages from the same web site often contain similar terms. The collection-related part of the similarity hinders clustering as it causes the creation of clusters that correspond to collections instead of topics. In this paper we present two methods to restrict clustering to the part of the similarity that is not associated with membership of a collection. Both methods can be used on top of standard clustering methods. Experiments on data sets with objects from multiple collections show that our methods result in better clusters than methods that do not take collection information into account.