We describe a set of experiments using machine learning techniques for the task of extractive summarisation. The research is part of a summarisation project for which we use a cor...
Archived biomedical literature and sequence data are growing rapidly. The Open Archives Initiative's Protocol for Metadata Harvesting (OAI-PMH) [1] provides a convenient way ...
After extracting terms from a corpus of titles and s in English, syntactic variation relations are identified amongst them in order to detect research topics. Three types of synta...
Discourse connectives are words or phrases such as once, since, and on the contrary that explicitly signal the presence of a discourse relation. There are two types of ambiguity t...
Abstract. We propose a generative model for automatic query reformulations from an initial query using the underlying subtopic structure of top ranked retrieved documents. We addre...
Debasis Ganguly, Johannes Leveling, Gareth J. F. J...