Besides tokenization, part-of-speech and named-entity-recognition this extension allows for dependency parsing, lemmatization (English and Spanish only) and sentiment analysis (English only). These mechanisms are using pre-trained language models and are based on the Stanford CoreNLP library (version 4.2.2).

Currently supported languages are:
English, German, French and Spanish.

Additionally to using pre-trained language models custom named-entity-tags can be defined to be used exlusively or along-side an existing model.