Natural language processing (NLP) is the part of AI that deals with human language: search, translation, chatbots, voice assistants, and text analysis. Language is hard for computers because meaning depends on context, word order, and tone, so the field is largely about finding good ways to represent text as numbers a model can learn from.
The lessons start with a big-picture overview of NLP, then look at word embeddings (Word2Vec), which turn words into vectors where similar words end up close together, and finish with sequence-to-sequence models, the encoder-decoder idea behind machine translation.
Watch the lessons in order. If a video runs long, feel free to treat it as a reference you dip back into later rather than something to finish in one sitting.
A quick, friendly overview of how computers process language: parsing sentences, understanding meaning, speech recognition, and the tasks NLP is used for.
Video 11minStatQuest shows how words become numbers a neural network can use, and how Word2Vec learns embeddings so that words used in similar contexts get similar values.
Video 16minHow an encoder-decoder network translates one sequence into another, such as English into Spanish, and the basic idea behind machine translation models.
Video 16min