Dimension Reduction in Natural Language – Darren Cook
NLP (Natural Language Processing) is a hot area at the moment, underlying technologies that have suddenly jumped in maturity, such as voice recognition and chat bots.
Word embeddings is one of the very few algorithms that is widely used across all types of state of the art NLP technologies. Neural nets are the most commonly used models for making word embeddings.
We will look at the algorithm in the context of dimension reduction.
The emphasis will be on training your intuition for understanding how it works, so you can more confidently know when to use it, and when not to. Also when to use pre-made embeddings and when to use your own.
We will also go multilingual, first looking at how it works in English, then in Japanese, giving us a chance to see which aspects are language-neutral, which aspects require special processing.
Darren Cook has over 20 years of experience as a software developer, data analyst, and technical director, working on everything from financial trading systems to NLP, data visualization tools, and PR websites for some of the world’s largest brands.
He is the author of two books for O’Reilly, one on low-latency data streaming, one on machine learning.
QQ Trend Ltd. is a data analysis and data products company, with global clients, mostly in the finance industry.