NLP/IR RESEARCH

FADEBAC: Fully Automatic DEnsity-BAsed Clustering applied to Sentiment Analysis more

Google 2013 European Doctoral Fellowship in Natural Language Processing Awarded to Thomas Müller more

Index based Statistical Analysis of Large Text Corpora more

Models of morphosyntax for statistical machine translation. The project aims to take advantage of recent progress in the automatic linguistic analysis of morphology and syntax for a new approach to statistical machine translation. more

Linguistic representations based on search engine results. Much of the success of statistical natural language processing applications hinges on the quality and quantity of the information that a given representational formalism makes available to the learning algorithm. more

In this project, a completely new infrastructure for the Humanities is developed for the exploitation of documentary sources (like images and retro-digitized text) as well as for the retrieval of empiric sources (like forms of speech). more

In der Abeitsgruppe von Prof. Schulz werden seit vielen Jahren Techniken untersucht, wie man auf der Basis semiautomatisch erstellter semantischer Netze in Texten (aus Archiven, Bibliotheken, Web) die dort auftretenden Themen nach Relevanz erfassen kann. more

Semi-supervised coreference resolution. We investigate two approaches to improving coreference resolution more

Development of a unified graph-theoretical system for acquiring lexico-semantic phenomena. The meaning of a word crucially depends on the relationships it has with other words. more