Embed, encode, attend, predict: The new deep learning formula for state-of-the-art NLP models
Explosion
NOVEMBER 9, 2016
This post explains the components of this new approach, and shows how they’re put together in two recent systems. Most NLP problems can be reduced to machine learning problems that take one or more texts as input. However, most NLP problems require understanding of longer spans of text, not just individual words.
Let's personalize your content