NeuralCoref is a pipeline extension for spaCy 2.1+ which annotates and resolves coreference clusters using a neural network. NeuralCoref is production-ready, integrated in spaCy's NLP pipeline and extensible to new training datasets. For a brief introduction to coreference resolution and NeuralCoref, please refer to our blog post. NeuralCoref is written in Python/Cython and comes with a pre-trained statistical model for English only. NeuralCoref is accompanied by a visualization client NeuralCoref-Viz, a web interface powered by a REST server that can be tried online.
Features
- MacOS / OS X · Linux · Windows (Cygwin, MinGW, Visual Studio)
- Python 3.6+ (only 64 bit)
- Documentation available
- Package managers: [pip]
- Install NeuralCoref from source
- Internals and Model
Categories
Machine LearningLicense
MIT LicenseFollow NeuralCoref
You Might Also Like
ConnectWise PSA (formerly Manage) allows you to stop working in separate systems, and helps you build a more profitable business. No more duplicate data entries, inefficient employees, manual invoices, and the inability to accurately track client service issues. Get a behind the scenes look into the award-winning PSA that automates processes for each area of business: sales, help desk, support, finance, and HR.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of NeuralCoref!