Beyond AI Models, Towards AI Systems

2020-11-24
  • 2,004

Biography

I am an assistant professor in the departments of artificial intelligence and computer science at Yonsei University. I received my Ph.D. degrees in Computer Science and Engineering from POSTECH, Korea in 2018. During my graduate study, I worked at Data Intelligence Lab with Prof. Seung-won Hwang and Algorithms Lab with Prof. Hee-Kap Ahn as my advisors. I was an intern at Adobe (San Jose, CA) in 2016 and 2015. My research area includes natural language and knowledge graphs.

Abstract

Recently, many works attempt to model machine reasoning and introduce commonsense reasoning datasets with expensive annotations. To boost performance from an arbitrary reasoning dataset, we present task augmentation by commonsense generation, in which the given dataset can be extended to multiple reasoning tasks without additional annotation efforts. For that, we adopt a commonsense knowledge generator which can be used to add new knowledge evidence to reasoning data samples. This approach is helpful to perturb and vary reasoning signals learned as different tasks, being jointly optimized by the cutting-edge of multi-task learning techniques.

 

ZOOM : https://zoom.us/j/8978217407?pwd=d1pOZmF1OWlseEdZRVBpV3VuSkl3dz09

ID : 897 821 7407

PW : 1nTQDY

LIST