This paper deals with an acronym/definition extraction approach from textual data (corpora) and the disambiguation of these definitions (or expansions). Both steps of our global pr...
We present a novel transition system for dependency parsing, which constructs arcs only between adjacent words but can parse arbitrary non-projective trees by swapping the order o...
Many NLP modules and applications require the availability of a module for wide-coverage inflectional analysis. One way to obtain such analyses is to use an morphological analyser...
A new type of language resource 'BAStat' has been released by the Bavarian Archive for Speech Signals. In contrast to primary resources like speech and text corpora BASt...
We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...