Same as CluProcessor but it includes custom tokenization and NER for the bio domain
Processor that uses only tools that are under Apache License Currently supports: tokenization (in-house), lemmatization (Morpha, copied in our repo to minimize dependencies), POS tagging (in-house BiMEMM), dependency parsing (ensemble of Malt models) for universal dependencies
Same as CluProcessor but using Stanford dependencies
CluProcessor for Portuguese
CluProcessor for Spanish