IS&T RCS Boot Camp - MATLAB Natural Language Processing

Human communication/knowledge is encoded with “natural language”; working with the encoded info computationally is known as “Natural Language Processing”. We will first look at a way of encoding words and how this encoding carries with it semantic meaning, “word2vec”. We will explore how we can then use the encoded semantic meaning to turn mathematical operations into linguistic ones. For example, it is possible to compute analogies simply using addition/subtraction. In the next part we will explore a breakthrough neural-network based NLP model called “GPT”. GPT first gained fame with the release of GPT-2; it simply tries to predict the next word in a sequence, however from this simple mechanism it is able to translate text, answer questions, summarizes passages, and generate text passages that can be indistinguishable from human-created ones. We will explore how to use GPT-2 based inference to do a variety of tasks. Throughout the Boot Camp attendees will work in small groups applying all these principles/techniques firsthand. At the end of the Boot Camp, each group will come up with a small project that applies the techniques learned in a novel way.