Stable release 1.0.5
This release include support for tagging, parsing, tokenizing, sentence splitting and lemmatizing of raw text.
It was evaluated during the CONLL Shared Task on Universal Dependencies Parsing and has pretrained languages models for the entire UD Corpus.
Features:
- configurable model store
- automatically download latest available models
- standalone server with support for preloading multiple languages: tutorial here
- easy pip installation package:
pip3 install nlpcube
- programmatic access through python API: tutorial here