NLP with word2vec, doc2vec... & gensim: Hands-on Workshop
Details
Target audience
Data Scientist; Python Developer; Natural Language Processing practitioner;
Meetup description
"NLP with word2vec, doc2vec...& gensim - Hands-on Workshop" by Lev Konstantinovskiy, Open Source Evangelist, R&D at RaRe Technologies
A hands-on introduction to the Natural Language Processing open-source library Gensim from its maintainer. We will apply 7 techniques for classifying movie plots by genre, including word2vec, doc2vec and other word embedding-based algorithms. No previous NLP knowledge is needed.
Please bring your laptop.
For requirements and Jupyter notebook see https://github.com/tmylk/movie-plots-by-genre
Warning: Requires a Google News word2vec model (https://docs.google.com/uc?id=0B7XkCwpI5KDYNlNUTTlSS21pQmM&export=download) (1.5Gb download). Please download the dataset before the workshop
What will you learn (bullet list) :
-
How to automatically assign tags to documents (for example, genres to movie plots).
-
Theory behind the word2vec algorithm.
-
How to use word2vec, doc2vec and 5 other document classification algorithms.
Presenter
Lev (https://uk.linkedin.com/in/levkonst), an expert in natural language processing, is a Python and Java developer. Lev has extensive experience working with financial institutions and is RaRe’s manager of open source communities including gensim, an open source machine learning toolkit for understanding human language.