In the research project EPOS1 we build a pro-active, contextsensitive support system to aid the user with his knowledge work, which is mostly about searching, reading, creating, an...
Retrieval accuracy can be improved by considering which document type should be filtered out and which should be ranked higher in the result list. Hence, document type can be used...
We formulate the problem of nonprojective dependency parsing as a polynomial-sized integer linear program. Our formulation is able to handle non-local output features in an effici...
This paper presents a new term extraction approach using relevance between term candidates calculated by a link analysis based method. Different types of relevance are used separa...
We derive two variants of a semi-supervised model for fine-grained sentiment analysis. Both models leverage abundant natural supervision in the form of review ratings, as well as...