Make interactive visualisations to figure out 'what lies' in word embeddings.

This small library offers tools to make visualisation easier of both word embeddings as well as operations on them. It has support for spaCy prebuilt models as a first class citizen but also offers support for sense2vec. There's a convenient API to perform linear algebra as well as support for popular transformations like PCA/UMAP/etc.


from whatlies import EmbeddingSet from whatlies.language import SpacyLanguage lang = SpacyLanguage('en_core_web_md') words = ['cat', 'dog', 'fish', 'kitten', 'man', 'woman', 'king', 'queen', 'doctor', 'nurse'] emb = lang[words] emb.plot_interactive(x_axis='man', y_axis='woman')

Author info

Vincent D. Warmerdam


Categories visualizers research

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 label on the issue tracker.

Read the docsJSON source