Institute of Information Science, Academia Sinica



Press Ctrl+P to print from browser


Generating Summary and Stylish Description

  • LecturerProf. Min Sun (Department of Electrical Engineering, National Tsing Hua University.Chief AI Scientist in Appier Inc.)
    Host: Keh-Yih Su
  • Time2018-12-18 (Tue.) 10:00 – 12:00
  • LocationAuditorium106 at IIS new Building

Using AI to generate paragraphs has many applications. In ACL 2018, we develop a novel abstractive summarization method aiming at generating smooth summarization rather than only highlighting sentences from the main article. Moreover, in AAAI 2018, we develop a novel method to generate stylish (emotive) paragraph-level description given an image. We will go over these two recent work and discuss about future direction for generative model in NLP.



Dr. Min Sun is an associate professor in the Department of Electrical Engineering at National Tsing Hua University (NTHU). He recently also becomes the Chief Artificial Intelligence (AI) Scientist of Appier.
Dr. Sun has worked under some of the most influential AI leaders, including Andrew Ng, Fei-Fei Li and Silvio Savarese. He contributed crowdsourcing ideas to the revolutionary ImageNet project led by Fei-Fei Li in 2009, and he is also an early contributor to the Robot Operating System (ROS) and Microsoft Kinect's human pose estimation system.
Dr. Sun was on the team led by Fei-Fei Li, working on the revolutionary ImageNet
project in 2009. He also holds 2 U.S. patents. In 2017, he led a summer research project featuring creativity in AI with Appier, which was subsequently accepted by the prestigious AAAI 2018. In the past three years, he published 22 top AI conference papers from Taiwan.
His areas of expertise are computer vision, natural language processing, deep learning, and reinforcement learning, while his research interests include 3D object recognition, human pose estimation, scene understanding, video understanding, and text summarization.
In 2016, Dr. Sun won the Digital Drift Best Paper on Deep Learning for Visual Analysis (1st and 2nd place). From 2015-2017, Dr. Sun has won CVGIP Best Paper Awards three times in a row. He is also the latest recipient of the Creative Young Scholar Award from the Foundation for the Advancement of Outstanding Scholarship in Taiwan. Before joining NTHU, he was a postdoctoral fellow in Computer Science & Engineering at the University of Washington.
Dr. Sun received his Ph.D in Electrical Engineering: System from the University of Michigan and his M.S in Electrical Engineering from Stanford University.