Natural Language Understanding
Humans understand natural language texts and discourses so effortlessly that we hardly ever think about it. For machines, however, the task of interpreting natural language, especially grasping meaning beyond the literal content, has proven extremely difficult. Our goal is to advance automatic methods towards a human-like understanding of natural language. To this end, we follow an approach that brings together methods and insights from Natural Language Processing and Semantic Web research.
We are actively involved in the specification of an ontology lexicon model and in the creation and automatic acquisition of ontology lexica. Exploiting such lexica, we explore how the interpretation process can be guided and supported by an ontology, which then provides the necessary domain knowledge for drawing inferences.
We also explore how semantic parsers can be automatically learned, and how the developed interpretation tools can be applied to, e.g., question answering over Semantic Web data.