An Introduction to Word Embeddings

clique na imagem para seguir o link

bom texto sobre uma técnica em NLP – Natural Language Pocessing

Part 1: Applications

Written by Aaron Geelon So

If you already have a solid understanding of word embeddings and are well into your data science career, skip ahead to the next part!

Human language is unreasonably effective at describing how we relate to the world. With a few, short words, we can convey many ideas and actions with little ambiguity. Well, mostly.

Because we’re capable of seeing and describing so much complexity, a lot of structure is implicitly encoded into our language. It is no easy task for a computer (or a human, for that matter) to learn natural language, for it entails understanding how we humans observe the world, if not understanding how to observe the world.

For the most part, computers can’t understand natural language. Our programs are still line-by-line instructions telling a computer what to do — they often miss nuance and context. How can you explain sarcasm to a machine?

There’s good news though. There’s been some important breakthroughs in natural language processing (NLP), the domain where researchers try to teach computers human language.

Tags: , ,

Comments are closed.