The Stanford NLP Group's official Python NLP library. It contains support for running various accurate natural language processing tools on 60+ languages and for accessing the Java Stanford CoreNLP software from Python. For detailed information please visit our official website.

🔥  A new collection of biomedical and clinical English model packages are now available, offering seamless experience for syntactic analysis and named entity recognition (NER) from biomedical literature text and clinical notes. For more information, check out our Biomedical models documentation page.

References

If you use this library in your research, please kindly cite our ACL2020 Stanza system demo paper:

@inproceedings{qi2020stanza,
    title={Stanza: A {Python} Natural Language Processing Toolkit for Many Human Languages},
    author={Qi, Peng and Zhang, Yuhao and Zhang, Yuhui and Bolton, Jason and Manning, Christopher D.},
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
    year={2020}
}

If you use our biomedical and clinical models, please also cite our Stanza Biomedical Models description paper:

@article{zhang2021biomedical,
    author = {Zhang, Yuhao and Zhang, Yuhui and Qi, Peng and Manning, Christopher D and Langlotz, Curtis P},
    title = {Biomedical and clinical {E}nglish model packages for the {S}tanza {P}ython {NLP} library},
    journal = {Journal of the American Medical Informatics Association},
    year = {2021},
    month = {06},
    issn = {1527-974X}
}

The PyTorch implementation of the neural pipeline in this repository is due to Peng Qi (@qipeng), Yuhao Zhang (@yuhaozhang), and Yuhui Zhang (@yuhui-zh15), with help from Jason Bolton (@j38), Tim Dozat (@tdozat) and John Bauer (@AngledLuffa). Maintenance of this repo is currently led by John Bauer.

If you use the CoreNLP software through Stanza, please cite the CoreNLP software package and the respective modules as described here ("Citing Stanford CoreNLP in papers"). The CoreNLP client is mostly written by Arun Chaganty, and Jason Bolton spearheaded merging the two projects together.

If you use the Semgrex or Ssurgeon part of CoreNLP, please cite our GURT paper on Semgrex and Ssurgeon:

@inproceedings{bauer-etal-2023-semgrex,
    title = "Semgrex and Ssurgeon, Searching and Manipulating Dependency Graphs",
    author = "Bauer, John  and
      Kiddon, Chlo{\'e}  and
      Yeh, Eric  and
      Shan, Alex  and
      D. Manning, Christopher",
    booktitle = "Proceedings of the 21st International Workshop on Treebanks and Linguistic Theories (TLT, GURT/SyntaxFest 2023)",
    month = mar,
    year = "2023",
    address = "Washington, D.C.",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.tlt-1.7",
    pages = "67--73",
    abstract = "Searching dependency graphs and manipulating them can be a time consuming and challenging task to get right. We document Semgrex, a system for searching dependency graphs, and introduce Ssurgeon, a system for manipulating the output of Semgrex. The compact language used by these systems allows for easy command line or API processing of dependencies. Additionally, integration with publicly released toolkits in Java and Python allows for searching text relations and attributes over natural text.",
}

Issues and Usage Q&A

To ask questions, report issues or request features 🤔, please use the GitHub Issue Tracker. Before creating a new issue, please make sure to search for existing issues that may solve your problem, or visit the Frequently Asked Questions (FAQ) page on our website.

Contributing to Stanza

We welcome community contributions to Stanza in the form of bugfixes 🛠️ and enhancements 💡! If you want to contribute, please first read our contribution guideline.

Installation

pip

Stanza supports Python 3.6 or later. We recommend that you install Stanza via pip, the Python package manager. To install, simply run:

pip install stanza

This should also help resolve all of the dependencies of Stanza, for instance PyTorch 1.3.0 or above.

If you currently have a previous version of stanza installed, use:

pip install stanza -U

Anaconda

To install Stanza via Anaconda, use the following conda command:

conda install -c stanfordnlp stanza

Note that for now installing Stanza via Anaconda does not work for Python 3.10. For Python 3.10 please use pip installation.

From Source

Alternatively, you can also install from source of this git repository, which will give you more flexibility in developing on top of Stanza. For this option, run

git clone https://github.com/stanfordnlp/stanza.git
cd stanza
pip install -e .

Running Stanza

Getting Started with the neural pipeline

To run your first Stanza pipeline, simply following these steps in your Python interactive interpreter:

>>> import stanza
>>> stanza.download('en')       # This downloads the English models for the neural pipeline
>>> nlp = stanza.Pipeline('en') # This sets up a default neural pipeline in English
>>> doc = nlp("Barack Obama was born in Hawaii.  He was elected president in 2008.")
>>> doc.sentences[0].print_dependencies()

If you encounter requests.exceptions.ConnectionError, please try to use a proxy:

>>> import stanza
>>> proxies = {'http': 'http://ip:port', 'https': 'http://ip:port'}
>>> stanza.download('en', proxies=proxies)  # This downloads the English models for the neural pipeline
>>> nlp = stanza.Pipeline('en')             # This sets up a default neural pipeline in English
>>> doc = nlp("Barack Obama was born in Hawaii.  He was elected president in 2008.")
>>> doc.sentences[0].print_dependencies()

The last command will print out the words in the first sentence in the input string (or Document, as it is represented in Stanza), as well as the indices for the word that governs it in the Universal Dependencies parse of that sentence (its "head"), along with the dependency relation between the words. The output should look like:

('Barack', '4', 'nsubj:pass')
('Obama', '1', 'flat')
('was', '4', 'aux:pass')
('born', '0', 'root')
('in', '6', 'case')
('Hawaii', '4', 'obl')
('.', '4', 'punct')

See our getting started guide for more details.

Accessing Java Stanford CoreNLP software

Aside from the neural pipeline, this package also includes an official wrapper for accessing the Java Stanford CoreNLP software with Python code.

There are a few initial setup steps.

• Download Stanford CoreNLP and models for the language you wish to use
• Put the model jars in the distribution folder
• Tell the Python code where Stanford CoreNLP is located by setting the CORENLP_HOME environment variable (e.g., in *nix): export CORENLP_HOME=/path/to/stanford-corenlp-4.5.3

We provide comprehensive examples in our documentation that show how one can use CoreNLP through Stanza and extract various annotations from it.

Online Colab Notebooks

To get your started, we also provide interactive Jupyter notebooks in the demo folder. You can also open these notebooks and run them interactively on Google Colab. To view all available notebooks, follow these steps:

• Go to the Google Colab website
• Navigate to File -> Open notebook, and choose GitHub in the pop-up menu
• Note that you do not need to give Colab access permission to your GitHub account
• Type stanfordnlp/stanza in the search bar, and click enter

Trained Models for the Neural Pipeline

We currently provide models for all of the Universal Dependencies treebanks v2.8, as well as NER models for a few widely-spoken languages. You can find instructions for downloading and using these models here.

Batching To Maximize Pipeline Speed

To maximize speed performance, it is essential to run the pipeline on batches of documents. Running a for loop on one sentence at a time will be very slow. The best approach at this time is to concatenate documents together, with each document separated by a blank line (i.e., two line breaks \n\n). The tokenizer will recognize blank lines as sentence breaks. We are actively working on improving multi-document processing.

Training your own neural pipelines

All neural modules in this library can be trained with your own data. The tokenizer, the multi-word token (MWT) expander, the POS/morphological features tagger, the lemmatizer and the dependency parser require CoNLL-U formatted data, while the NER model requires the BIOES format. Currently, we do not support model training via the Pipeline interface. Therefore, to train your own models, you need to clone this git repository and run training from the source.

For detailed step-by-step guidance on how to train and evaluate your own models, please visit our training documentation.

LICENSE

Stanza is released under the Apache License, Version 2.0. See the LICENSE file for more details.