We have a DEMO website (http://opennre.thunlp.ai/). Try it out!

OpenNRE is an open-source and extensible toolkit that provides a unified framework to implement relation extraction models. This package is designed for the following groups:

• New to relation extraction: We have hand-by-hand tutorials and detailed documents that can not only enable you to use relation extraction tools, but also help you better understand the research progress in this field.
• Developers: Our easy-to-use interface and high-performance implementation can acclerate your deployment in the real-world applications. Besides, we provide several pretrained models which can be put into production without any training.
• Researchers: With our modular design, various task settings and metric tools, you can easily carry out experiments on your own models with only minor modification. We have also provided several most-used benchmarks for different settings of relation extraction.
• Anyone who need to submit an NLP homework to impress their professors: With state-of-the-art models, our package can definitely help you stand out among your classmates!

This package is mainly contributed by Tianyu Gao, Xu Han, Shulian Cao, Lumin Tang, Yankai Lin, Zhiyuan Liu

Relation extraction is a natural language processing (NLP) task aiming at extracting relations (e.g., founder of) between entities (e.g., Bill Gates and Microsoft). For example, from the sentence Bill Gates founded Microsoft, we can extract the relation triple (Bill Gates, founder of, Microsoft).

Relation extraction is a crucial technique in automatic knowledge graph construction. By using relation extraction, we can accumulatively extract new relation facts and expand the knowledge graph, which, as a way for machines to understand the human world, has many downstream applications like question answering, recommender system and search engine.

A good research work is always accompanied by a thorough and faithful reference. If you use or extend our work, please cite the following paper:

@inproceedings{han-etal-2019-opennre,
    title = "{O}pen{NRE}: An Open and Extensible Toolkit for Neural Relation Extraction",
    author = "Han, Xu and Gao, Tianyu and Yao, Yuan and Ye, Deming and Liu, Zhiyuan and Sun, Maosong",
    booktitle = "Proceedings of EMNLP-IJCNLP: System Demonstrations",
    year = "2019",
    url = "https://www.aclweb.org/anthology/D19-3029",
    doi = "10.18653/v1/D19-3029",
    pages = "169--174"
}

It's our honor to help you better explore relation extraction with our OpenNRE toolkit!

If you want to learn more about neural relation extraction, visit another project of ours (NREPapers).

You can refer to our document for more details about this project.

We are now working on deploy OpenNRE as a Python package. Coming soon!

Clone the repository from our github page (don't forget to star us!)

git clone https://github.com/thunlp/OpenNRE.git

If it is too slow, you can try

git clone https://github.com/thunlp/OpenNRE.git --depth 1

Then install all the requirements:

pip install -r requirements.txt

Then install the package with

python setup.py install 

If you also want to modify the code, run this:

python setup.py develop

Note that we have excluded all data and pretrain files for fast deployment. You can manually download them by running scripts in the benchmark and pretrain folders. For example, if you want to download FewRel dataset, you can run

bash benchmark/download_fewrel.sh

Add OpenNRE directory to the PYTHONPATH environment variable, or open a python session under the OpenNRE folder. Then import our package and load pre-trained models.

>>> import opennre
>>> model = opennre.get_model('wiki80_cnn_softmax')

Note that it may take a few minutes to download checkpoint and data for the first time. Then use infer to do sentence-level relation extraction

>>> model.infer({'text': 'He was the son of Máel Dúin mac Máele Fithrich, and grandson of the high king Áed Uaridnach (died 612).', 'h': {'pos': (18, 46)}, 't': {'pos': (78, 91)}})
('father', 0.5108704566955566)

You will get the relation result and its confidence score.

For higher-level usage, you can refer to our document.

If you want to receive our update news or take part in discussions, please join our Google Group