Release 4.0.4

• Debugging regarding the update of the library sparse.
• Refactoring.

Release 4.0.3

• Stemming helper functions updated.

Release 4.0.2

• Fixed bugs in CLI.

Release 4.0.1

• Use classmethods to load pretrained models.
• Code optimization.

Release 4.0.0

• Removed support for Python 3.9 and 3.10;
• New style of documentation;
• New docstrings;
• Type hinting;
• Dependence on gensim reduced to topic modeling related functions and Word2Vec embedding;
• Modernizing the use of keras;
• The use of loguru, orjson, sparse and npdict libraries;
• Code cleanup and debugged;
• Removed the old implementation of document-term matrix, and replaced it with NumpyDocumentTermMatrix;
• Implementation of cosine similarity optimized by numba instead using the cosine distance from scipy;
• All unit tests and regression tests rewritten, and run by pytest.

Release 3.1.1

• Updates to Github actions.

Release 3.1.0

• Support for Python 3.13;
• Removal of dependence on nptyping.

Release 3.0.1

• Small bugs fixed.

Release 3.0.0

• Introduction of Github workflow, publishing package directly to PyPI from Github;
• Removal of Sakiguchi spell corrector; (refer to the examples\ folder in the repository)
• Removal of WrappedBERTEncoder and BERTScorer; (they can be installed from the package shorttext-bert)
• Update of documentation.

Release 2.2.1

• Code cleanup for token categorization. (Acknowledgements: Minseo Kim)