French. Unitex (▇▇▇▇▇▇▇, 2010) is a corpus processor implementing finite state technology that can be used for sentence splitting and tokenization for French. It can be freely downloaded and contains resources for various languages. TreeTagger (▇▇▇▇▇▇, 1997) is a language independent, probabilistic part-of-speech tagger, that uses decision trees to disambiguate word forms (POS). The tool has been adapted to French and a parameter file for FR is available from the author‘s site. The error-driven transformation-based ▇▇▇▇▇ POS tagger (▇▇▇▇▇, 1995) has also been adapted to French and can be downloaded from the website of the ATILF-CNRS NLP group12.
Appears in 2 contracts
Sources: Grant Agreement, Grant Agreement