Deep NLP basics
Hopefully, you're excited about chatbots and their potential applications, so let's now get to the boring details of NLP building blocks and standard approaches. As with almost everything in ML, deep NLP is experiencing hype and is evolving at a fast pace, so this section just scratches the surface and covers the most common and standard building blocks. For a more detailed description, Richard Socher's online course CS224d (http://cs224d.stanford.edu) is a really good starting point.
Recurrent Neural Networks
NLP has its own specificities that make it different from computer vision or other domains. One such feature is the processing of variable-length objects. At various levels, NLP is dealing with objects that could have different lengths, for example, a word in a language could contain several characters. Sentences are formed from variable-length word sequences. Paragraphs or documents consist of varying amounts of sentences. Such variability...