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 28556
공지 <12/8(Thu.) 11:00am>노벨상 소개 강연 - 2016년 노벨 물리학상: 위상 응집 물리의 탄생 2016.11.28 976467
325 <Oct. 11(Wed.) 4:30 PM> Graphene Membrane for Imaging Molecular Assembly and Dynamics 2017.09.27 47281
324 <Oct. 18(Wed.) 4:30 PM> AlGaN/GaN HEMT 센서플랫폼 (KANCSensGaNTM) 기술 소개 file 2017.10.11 48259
323 <May.1(Wed.)> Introduction of AMS Application 2019.04.24 48452
322 <June 7(Wed.) 4:30 PM> 물리학으로 보는 인간과 사회 2017.05.31 48667
321 <April. 12 (Wed.) 4:30 PM>디랙물질을 통해서 본 강상관 계의 양자 홀로그래피적 조명: 2017.04.05 48871
320 <May 31(Wed.) 4:30 PM>중력파, 새로운 천문학과 물리학의 시작 2017.05.24 49295
319 <Mar.20(Wed.)> Connecting Thermoelectricity and Superconductivity by Pressure Bridge 2019.03.13 50022
318 <May 24(Wed.) 4:30 PM>누구나 과학을 통찰하는 법 2017.05.17 50126
317 <June.5(Wed.)> Fluid gravity duality 2019.05.29 50804
316 <Nov.18(Wed.)>When Physics meets the Living Cells 2020.11.11 50890
315 <Dec.13(Wed.) 4:30 PM>기본에 충실하고 새로움에 도전한다 - 자율주행자동차의 핵심 기술들 – 2017.12.07 51375
314 <May.2(Wed.) 4:30 PM> Machine learning and statistical physics 2018.04.23 51571
313 <Nov. 9(Wed.) 4:30 PM> 20-nm resolution imaging of brain circuitry by next-generation expansion microscopy 2016.11.02 51860
312 <June 1(Wed.) 4:30 PM> 중력으로 강한 핵력 이해하기 2016.05.26 51926
311 <Dec. 14(Wed.) 4:30 PM>중력과 양자 얽힘 (tentative) 2016.12.07 51995
310 <May. 18(Wed.) 4:30 PM> Search for Hidden Neutrinos at the High Energy Frontier 2016.05.23 52093
309 <Mar. 15(Wed.) 4:30 PM>반도체 Fab Process와 물리학 전공자 2017.03.14 52157
308 <May. 4(Wed.) 4:30 PM> 플라즈마를 이용한 표면처리 기술 2016.04.27 52328
307 <April. 27(Wed.) 4:30 PM> 로봇과 함께 살아갈 미래 2016.04.22 52458
306 <Nov. 2(Wed.) 4:30 PM> 현대 우주론 이론과 관찰 (Theories and observations of modern cosmology) 2016.10.19 52473