Age | Commit message (Collapse) | Author |
|
* Added option to extract and pass word/document embeddings for faster iteration
* Focused on making the documentation a bit nicer (visualizations, etc. )
* Fixed #71
* Fixed #122, #136
|
|
* Major speedup, up to 2x to 5x when passing multiple documents (for MMR and MaxSum) compared to single documents
* Same results whether passing a single document or multiple documents
* MMR and MaxSum now work when passing a single document or multiple documents
* Improved documentation
* Added 🤗 Hugging Face Transformers
* Highlighting support for Chinese texts
* Now uses the CountVectorizer for creating the tokens
* This should also improve the highlighting for most applications and higher n-grams
* Fix #106
* Fix #116
|
|
|
|
* Added CountVectorizer tips and tricks page, including `KeyphraseVectorizers`
* Added general styling: `black`, `flake8`, `pre-commit`
|
|
* Guided KeyBERT
* Update default SBERT model
|
|
* Use paraphrase-MiniLM-L6-v2 as the default embedding model
* Highlight a document's keywords
* Added FAQ
|
|
* Use candidate words instead of extracting those from the documents
* Spacy, Gensim, USE, and Custom Backends were added
* Improved imports
* Fix encoding error when locally installing KeyBERT #30
* Improved documentation (ReadMe & MKDocs)
* Add the main tutorial as a shield
* Typos #31, #35
|
|
* Add similarity scores to the output
* Add Flair as a possible back-end
* Update documentation + improved testing
|
|
|
|
* Add diversity parameter in max sum sim
* Remove 3.7 testing due to timeout errors
|
|
|
|
* Added MMR
* Update documentation and pypi version
|
|
|