NLP - Cube

Sentence Splitting, Tokenization, Lemmatization, Part-of-speech Tagging, Dependency Parsing and Named Entity Recognition for more than 50 languages

Universal Dependencies

NLPCube is fully compatible with Universal Dependencies CONLLU format. If interested in building custom models, please consult the UD Guidelines.

Open and customizable

You have access to our entire repository, so you can easily integrate your own models and algorithms. Also you can retrain the system at any time, using custom word-embeddings and hyperparameters


We keep NLPCube updated with cutting-age Machine Learning and Natural Language Processing models. You can checkout our repository for latest models.


Currently we are working on multiple tasks:


There are several ways to contribute:


If you use NLP-Cube in your research we would be grateful if you would cite the following paper:

NLP-Cube: End-to-End Raw Text Processing With Neural Networks, BoroČ™, Tiberiu and Dumitrescu, Stefan Daniel and Burtica, Ruxandra, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, Association for Computational Linguistics. p. 171--179. October 2018

or, for the bibtex format, please click here.