Xiaodan Zhu, a research scientist at the National Research Council Canada, will be presenting Deep Learning for Text Mining: Case Studies on Social Media and Medical Text.
"Deep Learning has showed to be a game-changing technology
in the past 3-5 years. It has started to invade the field of natural language of natural language processing.
In this talk, I will first discuss its applications on social media text analysis. I will go through a case study that detects sentiment in social media, which has a wide range of applications, including tracking sentiment towards products, movies, politicians; improving customer relation models; detecting happiness and well-being; and improving automatic dialogue systems. It has attracted extensive interest from both the academia and industry. I will describe NRC Canada's top-notch approaches that were ranked top in International competitions, and discuss our Deep Learning models. In addition, I will also discuss information extraction on medical texts using traditional approaches and the scope of exploring deep learning methods."