|Original author(s)||Radim Řehůřek|
|Stable release||0.12.1 / 20 July 2015|
|Type||Natural language processing|
Gensim is an open-source vector space modeling and topic modeling toolkit, implemented in the Python programming language, using NumPy, SciPy and optionally Cython for performance. It is specifically intended for handling large text collections, using efficient online algorithms.
Gensim includes implementations of tf–idf, random projections, deep learning with Google's word2vec and document2vec algorithms  (reimplemented and optimized in Cython), hierarchical Dirichlet processes (HDP), latent semantic analysis (LSA) and latent Dirichlet allocation (LDA), including distributed parallel versions.
Some of the online algorithms in gensim were also published in the PhD dissertation Scalability of Semantic Analysis in Natural Language Processing of Radim Řehůřek (2011).
- Topic Modelling for Humans 
- Deep learning with word2vec and gensim
- Radim Řehůřek and Petr Sojka (2010). Software framework for topic modelling with large corpora. Proc. LREC Workshop on New Challenges for NLP Frameworks.
- Interview with Radim Řehůřek, creator of gensim
- gensim academic citations
- gensim source code
- gensim mailing list
- Rehurek, Radim (2011). "Scalability of Semantic Analysis in Natural Language Processing" (PDF). http://radimrehurek.com/. Retrieved 27 January 2015.
my open-source gensim software package that accompanies this thesis
- Rehurek, Radim. "Gensim". http://radimrehurek.com/. Retrieved 27 January 2015.
Gensim's tagline: "Topic Modelling for Humans"
|This scientific software article is a stub. You can help Wikipedia by expanding it.|