korean english


Home > 게시판 > 세미나

이번 학기 콜로퀴움은 학교의 권고를 따라, 사회적 거리두기 단계와 연계하여 온라인 혹은 오프라인(온라인 방송 병행)으로 운영될 예정입니다.

첫번째 강연에는 성균관대학교 소프트웨어학과 박진영 교수님을 모시고 콜로퀴움을 개최하오니, 학과 구성원 여러분의 많은 참여를 부탁 드립니다.

코로나19 확산방지를 위해 다과는 제공하지 않습니다.


1. Title: Scaling laws in Natural Language Processing

2. Speaker: 박  진  영  교수님
(성균관대학교 소프트웨어학과)

3. Date & Time: Mar. 3. (Wed.) 2021.  4:30 PM

4. Place: Natural Science 1,  Room No. 31214

5. Abstract: Many artificial intelligence (AI), machine learning (ML), and natural language processing (NLP) models have seen successes in recent years. Based on these models, there are many good NLP applications such as machine translation, question answering and chatbot. But, we still have questions about the models. One of the questions is the relationship between model performance and several factors such as model size.
Scaling law (power-law) is a functional relationship between two quantities and has been identified in physics. It is also observed in NLP too. In this talk, I will introduce a language model that is an important model for NLP and the power-law distribution between the factors and performance of the model. I will also briefly introduce the convergence of ML and physics.

JinYeong Bak is an assistant professor in the colleague of computing at Sungkyunkwan
University. His research interests analyzing human behaviors from their conversations and building open-domain conversation models from the insights of the analysis. He worked at Microsoft Research Asia as a research intern and United Nations Global Pulse Lab Jakarta as a junior data scientist. He received Ph.D. and M.S. from the KAIST and a B.S. from Sungkyunkwan University. His research has been published in ACL, EMNLP, CHI, and ICWSM. His personal homepage: https://nosyu.github.io and lab homepage: https://hli.skku.edu

번호 제목 날짜 조회 수
공지 2022학년도 1학기 콜로퀴움 일정 2022.01.10 27060
공지 <12/8(Thu.) 11:00am>노벨상 소개 강연 - 2016년 노벨 물리학상: 위상 응집 물리의 탄생 2016.11.28 969129
345 <10/17> Graphitic Carbon Nanostructures 2008.10.27 98432
344 <5/27(수) 오후4:30분>Controlling phases in epitaxial transition metal oxide thin films 2015.05.21 98311
343 <4/27> RENO Reactor Neutrino Experiment 2011.04.18 98281
342 <5/16> 물리학자가 바라 본 단백질: 왜, 어떻게 연구하는가? 2012.05.10 98193
341 <6/8> 액체금속 및 물의 과냉각 현상과 국소구조와의 관계 : 정전기 공중부양 기술 및 dynamic diamond anvil cell 2011.06.07 97785
340 <4/4> Novel multi-bit magnetic tagging technique for high-throughput chemical analysis 2008.03.31 97669
339 <11/9> Bosons in high Tc superconductors: an experimental survey 2011.10.31 96414
338 <9/25> 청각의 물리학: 어떻게 노이즈를 극복하는가? 2013.09.16 96214
337 <12/5> Fluerenes with diversed structures and their applications 2008.12.02 95994
336 <3/26> Fractional Hall Physics of Epitaxial Graphene: 2010.03.19 95393
335 <9/11> Complex networks in technology, biology and sociology 2009.09.04 95354
334 2014학년도 1학기 콜로퀴움 일정 2014.03.03 95086
333 <6/1> Electron phonon coupling effect in 4d transition metal oxide magnetism 2011.05.26 94461
332 <April. 6(Wed.) 4:30 PM> Quantitative Determination of High Tc Superconductivity Mechanism 2016.03.31 93684
331 <6/2>백색 LED를 이용한 반도체조명에 관하여 2006.05.29 93032
330 <5/1> Entanglement and topological order in 1D and 2D systems 2013.04.18 92579
329 2016학년도 2학기 콜로퀴움 일정 2016.08.02 92442
328 <11/13> Computer-Aided Engineering for Nucleic Acid Nanostructures 2013.11.07 92315
327 <11/16> Study of carrier transport and charging effects in organic devices 2011.11.10 92152
326 <4/16> Lasers, Microscopes, and Superconductors: Laser Scanning Microscopy of Superconducting Circuits 2014.04.10 91972