Upgrade to Pro — share decks privately, control downloads, hide ads and more …
Sign up for free

Knowledge Distillation for BERT

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

Knowledge Distillation for BERT

Avatar for Scatter Lab Inc.

Scatter Lab Inc.

April 17, 2020

More Decks by Scatter Lab Inc.

See All by Scatter Lab Inc.
zeta introduction
Avatar for Scatter Lab Inc. scatterlab
0
2k
SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
Avatar for Scatter Lab Inc. scatterlab
0
4.5k
Adversarial Filters of Dataset Biases
Avatar for Scatter Lab Inc. scatterlab
0
2.3k
Sparse, Dense, and Attentional Representations for Text Retrieval
Avatar for Scatter Lab Inc. scatterlab
0
2.4k
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
2.6k
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList
Avatar for Scatter Lab Inc. scatterlab
0
2.4k
Open-Retrieval Conversational Question Answering
Avatar for Scatter Lab Inc. scatterlab
0
2.4k
What Can Neural Networks Reason About?
Avatar for Scatter Lab Inc. scatterlab
0
2.3k

Other Decks in Research

See All in Research
2026年度 生成AI を活用した論文執筆ガイド／ワークショップ / 2026 Academic Year Guide to Writing Papers Using Generative AI - Workshop
Avatar for Kenji Saito ks91
PRO
0
230
LLM の Attention 機構まとめ — 数式・計算量・メモリ
Avatar for プワー puwaer
8
2.6k
大規模言語モデルは誰を覚えているか / Who Do Large Language Models Memorize?
Avatar for Shotaro Ishihara upura
0
170
Source Code Diff Revolution
Avatar for Nikolaos Tsantalis tsantalis
0
140
高性能計算機クラスタを用いた大規模点群処理による森林の単木抽出と構造解析
Avatar for Kenta Itakura kentaitakura
1
130
多様なデータを許容し学習し続ける模倣学習 / Advanced Imitation Learning for VLA
Avatar for PRIN Lab prinlab
0
300
typst の使い方：言語学を研究する学生のために
Avatar for Tomoya gitomochang
0
580
論文紹介：Doc-to-LoRA: Learning to Instantly Internalize Contexts
Avatar for Yukako Nakano yukako_nakano
0
160
【ローカルAIに向き合う展示会vol.2】液体時間定数型モジュールを用いた オリジナルの双方向エンコーダーモデルNexteraBERT 推論速度向上検討並びにダウンストリーム評価
Avatar for Rikka Botan rikkabotan7
0
190
[ACL 2026 Demo] Fast-MIA: Efficient and Scalable Membership Inference for LLMs
Avatar for Shotaro Ishihara upura
0
120
SAM3を用いたコマ・吹き出しの 領域検出と分割構造からの読み順推定
Avatar for kzmssk kzmssk
0
120
Claude Code × autoresearch 実践
Avatar for 数理の弾丸 mathbullet
0
270

Featured

See All Featured
Scaling GitHub
Avatar for Zach Holman holman
464
140k
Odyssey Design
Avatar for Ryan Kendrick rkendrick25
PRO
2
800
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
Avatar for soudai sone soudai
PRO
68
57k
How People are Using Generative and Agentic AI to Supercharge Their Products, Projects, Services and Value Streams Today
Avatar for Helen Beal helenjbeal
1
310
Music & Morning Musume
Avatar for Bryan Veloso bryan
47
7.4k
The Director’s Chair: Orchestrating AI for Truly Effective Learning
Avatar for Mike Taylor tmiket
1
290
The Illustrated Guide to Node.js - THAT Conference 2024
Avatar for David Neal reverentgeek
1
470
Crafting Experiences
Avatar for Bethany Jepchumba bethany
1
310
A Tale of Four Properties
Avatar for Chris Coyier chriscoyier
163
24k
Designing Powerful Visuals for Engaging Learning
Avatar for Mike Taylor tmiket
1
540
Large-scale JavaScript Application Architecture
Avatar for Addy Osmani addyosmani
515
110k
Building AI with AI
Avatar for Ines Montani inesmontani
PRO
1
1.2k

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