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

Knowledge Distillation for BERT

Avatar for Scatter Lab Inc. Scatter Lab Inc.
April 17, 2020
Research
0
2.3k

Knowledge Distillation for BERT

Avatar for Scatter Lab Inc.

Scatter Lab Inc.

April 17, 2020
Tweet

More Decks by Scatter Lab Inc.

See All by Scatter Lab Inc.
zeta introduction
Avatar for Scatter Lab Inc. scatterlab
0
1.7k
SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
Avatar for Scatter Lab Inc. scatterlab
0
4k
Adversarial Filters of Dataset Biases
Avatar for Scatter Lab Inc. scatterlab
0
2.2k
Sparse, Dense, and Attentional Representations for Text Retrieval
Avatar for Scatter Lab Inc. scatterlab
0
2.3k
Weight Poisoning Attacks on Pre-trained Models
Avatar for Scatter Lab Inc. scatterlab
0
2.2k
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
Avatar for Scatter Lab Inc. scatterlab
0
2.4k
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList
Avatar for Scatter Lab Inc. scatterlab
0
2.3k
Open-Retrieval Conversational Question Answering
Avatar for Scatter Lab Inc. scatterlab
0
2.3k
What Can Neural Networks Reason About?
Avatar for Scatter Lab Inc. scatterlab
0
2.2k

Other Decks in Research

See All in Research
実行環境に中立なWebAssemblyライブマイグレーション機構/techtalk-2025spring
Avatar for Yuki Nakata chikuwait chikuwait
0
220
3D Gaussian Splattingによる高効率な新規視点合成技術とその応用
Avatar for Hide Matsuki muskie82
5
2.5k
Type Theory as a Formal Basis of Natural Language Semantics
Avatar for Daiki Matsuoka daikimatsuoka
1
220
データサイエンティストの就労意識～2015→2024 一般（個人）会員アンケートより
Avatar for The Japan DataScientist Society datascientistsociety
PRO
0
660
公立高校入試等に対する受入保留アルゴリズム（DA）導入の提言
Avatar for Shunya Noda shunyanoda
0
5.7k
チャッドローン：LLMによる画像認識を用いた自律型ドローンシステムの開発と実験 / ec75-morisaki
Avatar for yumulab yumulab
1
440
SSII2025 [SS2] 横浜DeNAベイスターズの躍進を支えたAIプロダクト
Avatar for 画像センシングシンポジウム ssii
PRO
7
3.4k
なめらかなシステムと運用維持の終わらぬ未来 / dicomo2025_coherently_fittable_system
Avatar for monochromegane monochromegane
0
270
Vision And Languageモデルにおける異なるドメインでの継続事前学習が性能に与える影響の検証 / YANS2024
Avatar for Sansan R&D sansan_randd
1
110
90 分で学ぶ P 対 NP 問題
Avatar for E869120 e869120
17
7.5k
Mathematics in the Age of AI and the 4 Generation University
Avatar for Mohammed Hachama hachama
0
160
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
Avatar for Shunsuke KITADA shunk031
12
8.1k

Featured

See All Featured
XXLCSS - How to scale CSS and keep your sanity
Avatar for Zaharenia Atzitzikaki sugarenia
248
1.3M
The Invisible Side of Design
Avatar for Vitaly Friedman smashingmag
299
51k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
Avatar for Dan Newman danielanewman
229
22k
Java REST API Framework Comparison - PWX 2021
Avatar for Matt Raible mraible
31
8.6k
Side Projects
Avatar for Sacha Greif sachag
455
42k
Fantastic passwords and where to find them - at NoRuKo
Avatar for Phil Nash philnash
51
3.3k
Testing 201, or: Great Expectations
Avatar for Joseph Mastey jmmastey
42
7.5k
The Straight Up "How To Draw Better" Workshop
Avatar for Dennis Kardys denniskardys
234
140k
Typedesign – Prime Four
Avatar for Hannes Fritz hannesfritz
42
2.7k
A better future with KSS
Avatar for Kyle Neath kneath
239
17k
Code Reviewing Like a Champion
Avatar for maltzj maltzj
524
40k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
Avatar for Vitaly Friedman smashingmag
252
21k

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