Standard natural language processing (NLP) is a messy and difficult affair. It requires teaching a computer about English-specific word ambiguities as well as the hierarchical sparse nature of words in sentences. At Stitch Fix, word vectors help computers learn from the raw text in customer notes. Our systems need to identify a medical professional when she writes that she "used to wear scrubs to work" and distill "taking a trip" into a Fix for vacation clothing. Applied appropriately, word vectors are dramatically more meaningful and more flexible than current techniques and let computers peer into text in a fundamentally new way. I'll speak about word2vec and related techniques and will try to convince you that word vectors give us a simple and flexible platform for understanding text.
Hosted jointly by BIDS and the D-Lab.
Speaker(s)
Christopher Moody
Data Scientist, Stitch Fix
Christopher is a scientist programmer with a background in statistics, astrophysics, and high-performance computing. He has made contributions to a range of fields through quantitative analyses of complex systems. His interests lie in making data-driven discoveries and communicating them with clear and intuitive visualization.