We present a review of some recently developed techniques in the field of natural language processing. This area has witnessed a confluence of approaches which are inspired by theories from linguistics and those which are inspired by theories from information theory: statistical language models are becoming more linguistically sophisticated and the models of language used by linguists are incorporating stochastic techniques to help resolve ambiguities. We include a discussion about the underlying similarities between some of these systems and mention two approaches to the evaluation of statistical language processing systems. 1 Introduction Within the last decade, a great deal of attention has been paid to techniques for processing large natural language copora. The purpose of much of this activity has been to refine computational models of language so that the performance of various technical applications can be improved (e.g. speech recognisers [67], speech synthesisers [32], optica...

We present Minimum Bayes-Risk word alignment for machine translation. This statistical, model-based approach attempts to minimize the expected risk of alignment errors under loss functions that measure alignment quality. We describe various loss functions, including some that incorporate linguistic analysis as can be obtained from parse trees, and show that these approaches can improve alignments of the English-French Hansards.

Ist die Stelle des Leiters des Projektes befristet? � � nein � ja, befristet bis zum � eine weitere Beschäftigung ist vorgesehen bis zum 3.1.4 In dem Teilprojekt sind vorgesehen: • Untersuchungen am Menschen oder am menschlichen Material � ja � � nein Die erforderliche Zustimmung der zuständigen Ethikkommission liegt dem Antrag zum Teilprojekt in Kopie bei � ja � nein • klinische Studien im Bereich der somatischen Gentherapie � ja � � nein • Tierversuche � ja � � nein • gentechnologische Untersuchungen � ja � � nein • Untersuchungen an humanen embryonalen Stammzellen � ja � � nein Die gesetzliche Genehmigung liegt vor � ja � nein 3

This degree is submitted to the University of Cambridge