Title : Named Entity Recognition for Cultural Heritage
| Presenter | Marieke van Erp |
| Abstract | Named entities are the basic building blocks for any text understanding task. In recent years, data-driven, or statistical named entity recognition (NER) approaches have risen to the challenge of automatically recognising named entities in text. However, most NER work has been focused on the newswire domain, leaving many domains still in need of suitable NER tools to unlock information in their texts. Domain adaptation is therefore an important task, but it also provides some big challenges to current NER approaches. I will present a study into NER for the cultural heritage domain in of an in-depth comparison of two state-of-the-art statistical approaches. One approach employs advanced features describing domain knowledge, the second achieves domain adaptation through retraining with domain data. Although the re- sults with the domain-informed approach are promising, our comparison shows that currently using annotated training data is still the most promising form of domain adaptation. |
Title : A Safe-Mode for OWL Ontologies
| Presenter | Thomas Scharrenbach |
| Abstract | In the Semantic Web ontologies are used for modeling shared conceptualizations about a domain of discourse. Together with data they form a knowledge base. Yet, knowledge bases contain bugs, as they are created from different parts, created by different people, contain modeling artifacts, and use non-trivial formalism for inferencing. Ontologies have a sound logic formalism for inference, but bugs can cause the knowledge base to become inconsistent, which can make inference meaningless. Fixing those bugs, aka OWL-Debugging, requires re-writing parts of the knowledge base. To cope with situations where this is not desirable or even not feasible we introduce a safe-mode for knowledge bases. This safe-mode may limit certain services for the knowledge base while leaving the fundamental basics and the services as such unchanged. We show how the safe-mode can be implemented borrowing from Lehmann's Default Logics and Lukasiewicz' Probabilistic Description Logics. |