embed-clustering is a python package which uses different non-parametric methods and bert embeddings to identify groups of similar objects from textual data.
In this package, the Chinese restaurant process (CRP) is used along with the bert embeddings.
Pypi repo: https://pypi.org/project/embed-cluste...
GitHub repo: https://github.com/dreji18/embed-clus...
Authors: Masume Azizyan, Deepak John Reji
/ masume-azizian
/ deepak-john-reji
------------------------------------------------------------------------------------------------------------------------
Watch this similar tutorial on how clustering is done with bert embeddings and knn algorithm: • Clustering with Bert Embeddings