[세미나안내] Colloquium of our Department, Professor Jaegul Choo, Korea University, 2018 Oct 5 (Fri), 11:00~12:00am, #2501(Multi Media Room)
We're announcing a colloquium on the seminar of our department as below.
- Speaker : Jaegul Choo (Associate Professor at Dept. of Computer Science and Engineering at Korea University)
- Date & Time : 2018 Oct 5 (Fri), 11:00~12:00am
- VENUE : E2 Bld., Multi Media Room #2501
- Seminar Title : Reading Comprehension-based Question Answering via Deep Neural Networks with Attention and Memory Modules
A reading comprehension-based question answering task is an important cornerstone towards high-level artificial intelligence. This talk will present several recent approaches based on deep neural networks that tackle this task. Starting with the introduction to the task and its problem setting, I will present how the approach generally works in terms of LSTM/GRU encoding and self- and co-attention modules. Additionally, I will describe other approaches based on neural memory modules. Afterwards, I will focus on discussing my recent work called MemoReader (to appear in EMNLP'18), which effectively integrates a self-attention module and an advance neural memory architecture called differentiable neural computer. The talk will conclude with future research directions in question answering and other natural language processing domains.
Jaegul Choo (https://sites.google.com/site/jaegulchoo/ ) is an assistant professor in the Dept. of Computer Science and Engineering at Korea University. He has been a research scientist at Georgia Tech from 2011 to 2015, where he also received M.S in 2009 and Ph.D in 2013. His research covers broad areas including data mining, machine learning, visual analytics, computer vision, and natural language processing, and his work has been published in premier venues such as KDD, WWW, WSDM, CVPR, ECCV, EMNLP, AAAI, IJCAI, ICDM, ICWSM, SDM, TKDD, DMKD, KAIS, IEEE VIS, EuroVIS, CHI, TVCG, CFG, and CG&A. He earned the Best Student Paper Award at ICDM in 2016, the NAVER Young Faculty Award in 2015, the Outstanding Research Scientist Award at Georgia Tech in 2015, and the Best Poster Award at IEEE VAST (as part of IEEE VIS) in 2014.