Bernd Kiefer

Learn More
This paper describes new and improved techniques which help a unification-based parser to process input efficiently and robustly. In combination these methods result in a speed-up in parsing time of more than an order of magnitude. The methods are correct in the sense that none of them rule out legal rule applications. 1 I n t r o d u c t i o n This paper(More)
We present a novel, data-driven method for integrated shallow and deep parsing. Mediated by an XML-based multi-layer annotation architecture, we interleave a robust, but accurate stochastic topological field parser of German with a constraintbased HPSG parser. Our annotation-based method for dovetailing shallow and deep phrasal constraints is highly(More)
Tony Belpaeme, Paul Baxter, Robin Read, Rachel Wood Plymouth University, United Kingdom Heriberto Cuayáhuitl, Bernd Kiefer, Stefania Racioppa, Ivana Kruijff-Korbayová Deutsches Forschungszentrum für Künstliche Intelligenz, Germany Georgios Athanasopoulos, Valentin Enescu Vrije Universiteit Brussel, Belgium Rosemarijn Looije, Mark Neerincx Organization for(More)
We describe a novel method for coping with ungrammatical input based on the use of chart-like data structures, which permit anytime processing. Priority is given to deep syntactic analysis. Should this fail, the best partial analyses are selected, according to a shortest-paths algorithm, and assembled in a robust processing phase. The method has been(More)
f ur K unstliche Intelligenz GmbH, DFKI) in the Computational Linguistics area. I am grateful to these institutes for their support. Many, many people have helped me not to get lost during the development of this thesis. Hans Uszkoreit, my main supervisor, provided a motivating, enthusiastic, and critical atmosphere during the many discussions we had. It(More)
We present an architecture for the integration of shallow and deep NLP components which is aimed at flexible combination of different language technologies for a range of practical current and future applications. In particular, we describe the integration of a high-level HPSG parsing system with different high-performance shallow components, ranging from(More)
Large-scale grammar-based parsing systems nowadays increasingly rely on independently developed, more specialized components for pre-processing their input. However, different tools make conflicting assumptions about very basic properties such as tokenization. To make linguistic annotation gathered in pre-processing available to ‘deep’ parsing, a hybrid NLP(More)
This paper presents a framework for temporal representation and reasoning in the MUSING project ( which is dedicated to the investigation of semantic-based business intelligence solutions. Temporal information is based on a diachronic representation of time. Since ontological knowledge in MUSING is encoded in OWL (Smith, Welty,(More)