Are you interested in learning more about Natural Language Processing? Marco Bonzanini will be join this months London Python Group! Don't miss it!
Word embeddings are a family of Natural Language Processing (NLP) algorithms where words are mapped to vectors in low-dimensional space.
The interest around word embeddings has been on the rise in the past few years, because these techniques have been driving important improvements in many NLP applications like text classification, sentiment analysis or machine translation.
We're lucky to have Marco Bonzanini (author, and organiser PyData meetup) describe the intuitions behind this family of algorithms, in particular with details on word2vec and doc2vec.
We'll also explore some of the Python tools that allow us to implement modern NLP applications and we'll conclude with some practical considerations.
YOU MAY ALSO LIKE:
Word Embeddings for Natural Language Processing with Python
Marco a freelance Data Scientist based in London, UK. Backed by a PhD in Information Retrieval. He specialises in search applications and text analytics applications, and enjoys working on a broad range of information management and data science projects. Active in the PyData community, he helps co-organising the PyData London meetup.