How Deep Learning has Transformed Natural Language Processing orDid a Machine Really Say That?"
Friday, April 1, 9:00–10:30 a.m. EDT, via Zoom.
Distinguished Language Science Colloquium
Dr. Lee Giles
David Reese Professor at the School of Information Sciences and Technologyat Penn State
Deep learning (DL) is a rather new machine learning model strongly based on neural networks. It became popular primarily for performance reasons, especially when it strongly outperformed other machine learning methods, first in the areas of computer vision, then famously in natural language processing (NLP) such as machine translation, all in this decade. Since then, DL has continued to perform well on many large data problems and in related competitions and applications seem to be proliferating. That being said, there are many issues with Deep Learning. Here we will discuss its strengths and weaknesses with some in NLP and offer suggested research directions.