Software & Data
Tool for retrofitting (and thus improving) word vectors to semantic lexicons.
Suite of lexical semantic evaluation benchmarks.
Parallel literary corpus with T/V pronoun labels. German-English parallel corpus used for experiments on identifying formal vs. informal language address in English
German Named Entity Recognition. German classifiers for the Stanford CRF-based NER systems (optimized in April 2010) and manually annotated EUROPARL data as out-of-domain testset.