25
NLP in Python: Unleashing the power of spaCy
5:45 PM - 7:30 PMNortheastern University—Vancouver, 333 Seymour St, 8th Floor, Vancouver, BC V6B 5A7
Ever wonder about how to do natural language processing (NLP) in Python? In this talk, we explore spaCy — a pretty popular open-source library for NLP. Through a series of simple examples, we will understand how to use spaCy in a practical setting. In particular, we will look into common NLP tasks like tokenization, sentence segmentation, lemmatization, noun chunking, named entity recognition, etc. In the latter part of the talk, we will discuss how to extend spaCy’s capabilities by adding custom components to it through a worked example: a simple noun chunker based on spaCy’s part-of-speech (POS) tagging.
About the Speaker
Mario Garcia-Armas is a machine learning engineer at Flipboard, working primarily in natural language processing. In 2015, he received a PhD in Mathematics from the University of British Columbia, specializing in algebra and algebraic geometry. Before joining Flipboard, he worked at A Thinking Ape Inc. for 3+ years, where he built their recommendation engine and revenue prediction pipeline.