Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Knowledge Distillation for BERT

Scatter Lab Inc.
April 17, 2020
Research
0
2.1k

Knowledge Distillation for BERT

Scatter Lab Inc.

April 17, 2020
Tweet

More Decks by Scatter Lab Inc.

See All by Scatter Lab Inc.
SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
scatterlab
0
3.1k
Adversarial Filters of Dataset Biases
scatterlab
0
2.1k
Sparse, Dense, and Attentional Representations for Text Retrieval
scatterlab
0
2.1k
Weight Poisoning Attacks on Pre-trained Models
scatterlab
0
2k
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
scatterlab
0
2.2k
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList
scatterlab
0
2.1k
Open-Retrieval Conversational Question Answering
scatterlab
0
2.1k
What Can Neural Networks Reason About?
scatterlab
0
2.1k
Exploring the Limits of Transfer Learning with Unified Text-to-Text Transformer
scatterlab
0
2k

Other Decks in Research

See All in Research
Embodied AIについて / About Embodied AI
nttcom
1
510
Target trial emulationの概要
shuntaros
2
1.1k
20240209 データを肴に熊本の交通を考える会「車１割削減、渋滞半減、公共交通２倍」をめざし世界に学ぼう
trafficbrain
0
780
自己教師あり学習による事前学習（CVIMチュートリアル）
naok615
2
1.4k
VAR モデルによる OSS プロジェクト同士が生存性に与える 影響の分析
noppoman
0
130
People Driven Transformation / 人が起点の、社会の変え方
dmattsun
0
150
東工大Swallowプロジェクトにおける大規模日本語Webコーパスの構築
aya_se
12
6.3k
言語間転移学習で大規模言語モデルを賢くする
ikuyamada
6
1.8k
プロシェアリング白書2024_PROSHARING_REPORT_2024
circulation
0
600
Breaking Tradeoffs: Extremely Scalable Multi-Agent Pathfinding Algorithms
kei18
0
140
20240127_熊本から今いちど真面目に都市交通～めざせ「車1割削減、渋滞半減、公共交通2倍」～ 全国路面電車サミット2024宇都宮
trafficbrain
1
650
DeepCrysTet: A Deep Learning Approach Using Tetrahedral Mesh for Predicting Properties of Crystalline Materials
tsurubee
0
360

Featured

See All Featured
Creatively Recalculating Your Daily Design Routine
revolveconf
209
11k
Code Review Best Practice
trishagee
54
15k
Happy Clients
brianwarren
91
6.4k
ParisWeb 2013: Learning to Love: Crash Course in Emotional UX Design
dotmariusz
104
6.6k
The Invisible Side of Design
smashingmag
294
49k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
6
990
Product Roadmaps are Hard
iamctodd
43
9.7k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
1
1.3k
Intergalactic Javascript Robots from Outer Space
tanoku
266
26k
From Idea to $5000 a Month in 5 Months
shpigford
377
45k
Rails Girls Zürich Keynote
gr2m
91
13k
Building Better People: How to give real-time feedback that sticks.
wjessup
354
18k

Transcript

  1. ,OPXMFEHF%JTUJMMBUJPOGPS#&35 ੿਌੤ .BDIJOF-FBSOJOH4PGUXBSF&OHJOFFS

  2. ݾର ݾର  1BUJFOU,OPXMFEHF%JTUJMMBUJPOGPS#&35.PEFM$PNQSFTTJPO  %JTUJM#&35 BEJTUJMMFEWFSTJPOPG#&35TNBMMFS GBTUFS DIFBQFSBOEMJHIUFS 

    'BTU#&35B4FMGEJTUJMMJOH#&35XJUI"EBQUJWF*OGFSFODF5JNF  %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI

  3. 1BUJFOU,OPXMFEHF%JTUJMMBUJPO GPS#&35.PEFM$PNQSFTTJPO 1BUJFOU,OPXMFEHF%JTUJMMBUJPOGPS#&35.PEFM$PNQSFTTJPO

  4. • &./-1"DDFQUFE • .JDSPTPGU%ZOBNJDT"*3FTFBSDI • ୭ୡ#&35঑୷दب • ӝઓ,OPXMFEHF%JTUJMMBUJPOҗ׮ܰѱ1BUJFOUܳ੸ਊೣ • 4PGU5BSHFU݅੉ਊೞ૑ঋҊ׮ܲۨ੉যীࢲب೟णೞب۾ೣ

    1BUJFOU,OPXMFEHF%JTUJMMBUJPOGPS#&35.PEFM$PNQSFTTJPO 1,%GPS#FSU.PEFM$PNQSFTTJPO

  5. 1BUJFOU,OPXMFEHF%JTUJMMBUJPOGPS#&35.PEFM$PNQSFTTJPO ೟ण੹ۚ • ࣁо૑MPTTܳઙ೤ೣ • )BSEUBSHFUী؀ೠ$SPTT&OUSPQZ-PTT • 4PGU5BSHFU 5FBDIFSNPEFM੄PVUQVU ী؀ೠ$SPTT

    &OUSPQZ-PTT • ઺рۨ੉যٜ੄<$-4>ష௾੄SFQSFTFOBUJPOٜী؀ೠ OPSNBMJ[FE.FBO4RVBSFE-PTT

  6. ೟ण٣పੌ 1BUJFOU,OPXMFEHF%JTUJMMBUJPOGPS#&35.PEFM$PNQSFTTJPO • 4UVEFOU7BSJBUJPO#&35@ #&35@ • #&35@ CBTF ীࢲ୐Lѐ੄ۨ੉য۽4UVEFOUܳୡӝച •

    1,%4LJQFWFSZLMBZFSীࢲ೟ण • 1,%-BTUMBTULMBZFSীࢲ೟ण

  7. Ѿҗ 1BUJFOU,OPXMFEHF%JTUJMMBUJPOGPS#&35.PEFM$PNQSFTTJPO ؘ੉ఠ݆ਸٸੜؽ

  8. Ѿҗ 1BUJFOU,OPXMFEHF%JTUJMMBUJPOGPS#&35.PEFM$PNQSFTTJPO

  9. Ѿҗ 1BUJFOU,OPXMFEHF%JTUJMMBUJPOGPS#&35.PEFM$PNQSFTTJPO

  10. %JTUJM#&35 BEJTUJMMFEWFSTJPOPG#&35 TNBMMFS GBTUFS DIFBQFSBOEMJHIUFS %JTUJM#&35 BEJTUJMMFEWFSTJPOPG#&35TNBMMFS GBTUFS DIFBQFSBOEMJHIUFS

  11. • /FVS*14"DDFQUFE • )VHHJOHGBDF • 4UVEFOUݽ؛ীࢲUPLFOUZQFFNCFEEJOHT QPPMFSMBZFS࢏ઁ %JTUJM#&35 BEJTUJMMFEWFSTJPOPG#&35TNBMMFS GBTUFS

    DIFBQFSBOEMJHIUFS %JTUJM#&35

  12. %JTUJM#&35 BEJTUJMMFEWFSTJPOPG#&35TNBMMFS GBTUFS DIFBQFSBOEMJHIUFS ೟ण੹ۚ • -PTT • 4UVEFOU5FBDIFS$SPTT&OUSPQZ •

    .BTLFE-.-PTT • $PTJOF&NCFEEJOH-PTT • 4UVEFOU-BZFSܳпفѐ੄ۨ੉য׼ೞաঀஂೣ

  13. Ѿҗ %JTUJM#&35 BEJTUJMMFEWFSTJPOPG#&35TNBMMFS GBTUFS DIFBQFSBOEMJHIUFS

  14. Ѿҗ %JTUJM#&35 BEJTUJMMFEWFSTJPOPG#&35TNBMMFS GBTUFS DIFBQFSBOEMJHIUFS

  15. 'BTU#&35 "4FMGEJTUJMMJOH#&35XJUI"EBQUJWF*OGFSFODF5JNF 'BTU#&35B4FMGEJTUJMMJOH#&35XJUI"EBQUJWF*OGFSFODF5JNF

  16. • 5FODFOU3IJOP#JSE&MJUF5SBJOJOH1SPHSBNীࢲಎ٬߉ই੘ࢿػ֤ޙ • 4QFFE"DDVSBDZܳઑ੺оמೠ#&35.PEFMઁউ • "EBQUJWF*OGFSFODFооמೠ#&35 4FMG%JTUJMMJOHNFDIBOJTN 'BTU#&35B4FMGEJTUJMMJOH#&35XJUI"EBQUJWF*OGFSFODF5JNF 'BTU#&35

  17. 'BTU#&35B4FMGEJTUJMMJOH#&35XJUI"EBQUJWF*OGFSFODF5JNF ೟ण੹ۚ

  18. 'BTU#&35B4FMGEJTUJMMJOH#&35XJUI"EBQUJWF*OGFSFODF5JNF ೟ण੹ۚ • ೟णࣽࢲ • 1SFUSBJOJOH'JOF5VOJOH4FMGEJTUJMMBUJPO • 4FMG%JTUJMMBUJPOزউ୭࢚ਤ#SBODI৬ೞਤ#SBODI੄$SPTT&OUSPQZ҅࢑ • 6ODFSUBJOUZѐ֛بੑ

    • п-BZFS੄#SBODI߹۽6ODFSUBJOUZ҅࢑ • оࢸ6ODFSUBJOUZоծਸࣻ۾"DDVSBDZо֫׮

  19. Ѿҗ 'BTU#&35B4FMGEJTUJMMJOH#&35XJUI"EBQUJWF*OGFSFODF5JNF

  20. Ѿҗ 'BTU#&35B4FMGEJTUJMMJOH#&35XJUI"EBQUJWF*OGFSFODF5JNF

  21. Ѿҗ 'BTU#&35B4FMGEJTUJMMJOH#&35XJUI"EBQUJWF*OGFSFODF5JNF

  22. %ZOB#&35 %ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI

  23. • )VBXFJ/PBIsT"SL-BC • XJEUI EFQUIߑೱਵ۽"EBQUJWFೠ#&35ઁউ • 'VMM#&35.PEFMXJEUIBEBQUJWF#&35XJEUIEFQUIBEBQUJWF#&35ള۲ %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI %ZOB#&35

  24. %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI ೟ण੹ۚ

  25. %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI ೟ण੹ۚ

  26. %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI ೟ण੹ۚ

  27. %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI ೟ण੹ۚ • 8JEUI೟ण • 5FBDIFS੄4PGU5BSHFUҗ$SPTTFOUSPQZ ੐߬٬ۨ੉য )JEEFO-BZFSח.4& • %BUBBVHNFOUBUJPO੸ਊ

    • %FQUI೟ण • NPE E  N@E ੋۨ੉যܳESPQ • FYNVMUJUQMJFSח  ਸESPQ • MPTTחXJEUI৬э਷ؘXFJHIUח׮ܴ • ݃૑݄ীHSPVOEUSVUIMBCFMਸ$SPTT&OUSPQZܳݡৈࢲGJOFUVOJOH

  28. Ѿҗ %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI

  29. Ѿҗ %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI

  30. Ѿҗ %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI

  31. Ѿҗ %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI

  32. Ѿҗ %ZOB#&35%ZOBNJD#&35XJUI"EBQUJWF8JEUIBOE%FQUI

  33. хࢎ೤פ׮✌ ୶о૕ޙژחҾӘೠ੼੉੓׮ݶ঱ઁٚইېোۅ୊۽োۅ઱ࣁਃ ੿਌੤ .BDIJOF-FBSOJOH4PGUXBSF&OHJOFFS  &NBJMVLKBF!TDBUUFSMBCDPLS