Theoretical Computational Linguistics

	Institute for Natural Language Processing
	Theoretical Computational Linguistics

Resource Lists

Tools

SFST the Stuttgart Finite State Transducer tools for implementing morphological analysers and other FST-based tools
TreeTagger a language-independent part-of-speech tagger with parameter files for German, English, French and Italian
RFTagger a POS tagger for fine-grained tagsets with parameter files for German and Czech.
Tagger Chunker an annotation tool for nominal and verbal chunks based on the TreeTagger with parameter files for German and English
YAP a parser for feature-structure based grammars with a simple grammar development environment
LoPar a parser for lexicalised probabilistic context-free grammars
BitPar a parser for highly ambiguous probabilistic context-free grammars (like treebank grammars)
VPF a parse forest browser for feature grammars
LSC a statistical soft-clustering tool for predicate-argument tuples with a fixed number of arguments.
PAC a statistical soft-clustering tool for predicate-argument tuples with a variable number of arguments. Selectional preferences are generalised by means of WordNet concepts.

Lexicon Induction

Lexical Information for English subcategorisation and Viterbi parses learned by the English statistical grammar model
Lexical Information for German frequencies, subcategorisation and Viterbi parses learned by the German statistical grammar model
Semantically Annotated Lexica German and English lexica of subcat-frames annotated with cluster-based slot-labels

Resource Application