spaCy's NER model
spaCy v2.0’s Named Entity Recognition system features a sophisticated word embedding strategy using subword features and “Bloom” embeddings, a deep convolutional neural network with residual connections, and a novel transition-based approach to named entity parsing. The system is designed to give a good balance of efficiency, accuracy and adaptability. In this talk, I sketch out the components of the system, explaining the intuition behind the various choices. I also give a brief introduction to the named entity recognition problem, with an overview of what else Explosion AI is working on, and why.
Categories videos
Found a mistake or something isn't working?
If you've come across a universe project that isn't working or is incompatible with the reported spaCy version, let us know by opening a discussion thread.
Submit your project
If you have a project that you want the spaCy community to make use of, you can suggest it by submitting a pull request to the spaCy website repository. The Universe database is open-source and collected in a simple JSON file. For more details on the formats and available fields, see the documentation. Looking for inspiration your own spaCy plugin or extension? Check out the project idea section in Discussions.