We explore how lexical and ontological relations can be acquired automatically from natural language questions. The focus in this paper is on identifying hyponym and meronym relations by using simple pattern matching. It is shown that natural language questions can provide a significant source for ontological information.
In this paper we propose an architecture for dialogue systems that incorporate information extraction, thereby providing natural and efficient access to unstructured information sources. A key feature of the architecture is the use of ontologies as shared domain knowledge sources. We discuss how ontologies can be used for various tasks. with focus on… (More)
This paper presents a re-examiniation of previous work on machine learning techniques for questions classification, as well as results from new experiments. The results suggest that some of the work done in the field have yielded biased results. The results also suggest that Na¨ıve Bayes, Decision Trees and Support Vector Machines perform on par with each… (More)
Question answering systems can be seen as the next step in information retrieval, allowing users to pose questions in natural language and receive succinct answers. In order for a question answering system as a whole to be successful, research has shown that the correct classification of questions with regards to the expected answer type is imperative.… (More)
This paper reviews plan-based models of dialogue. The original model is thoroughly presented. Important developments of the original model are also presented. Finally, benefits and drawbacks of plan-based approaches to dialogue modelling are discussed.
Supporting the cooperation of people in large organizations which are distributed geographically is one of the great challenges for the CSCW research. Technology launched a framework in which telecooperation applications will be developed to support the distributed government in Bonn and Berlin. POLITeam is one project embedded in that framework. Its aim is… (More)