Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
文献紹介:Auxiliary Objectives for Neural Error Dete...
Search
Atsushi
December 21, 2018
Technology
100
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
文献紹介:Auxiliary Objectives for Neural Error Detection Models
2018/12/21 文献紹介
長岡技術科学大学
自然言語処理研究室
Atsushi
December 21, 2018
More Decks by Atsushi
See All by Atsushi
文献紹介:Automated Evaluation of Out-of-Context Errors
atsumikan
0
110
文献紹介:Correction of OCR Word Segmentation Errors in Articles from the ACL Collection through Neural Machine Translation Methods
atsumikan
0
180
文献紹介:Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection
atsumikan
0
140
文献紹介:Low-resource OCR error detection and correction in French Clinical Texts
atsumikan
0
140
文献紹介:CMMC-BDRC Solution to the NLP-TEA-2018 Chinese Grammatical Error Diagnosis Task
atsumikan
0
140
文献紹介 : Fluency Boost Learning and Inference for Neural Grammatical Error Correction
atsumikan
0
200
文献紹介:語彙の概念化と Wikipediaを用いた英字略語の意味推定方法
atsumikan
0
170
文献紹介:The Effect of Error Rate in Artificially Generated Data for Automatic Preposition and Determiner Correction
atsumikan
0
150
文献紹介: Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction
atsumikan
0
210
Other Decks in Technology
See All in Technology
ポケモン対戦を自動で記録して振り返ろう
fufufukakaka
0
310
書き手が人でもAIでも正しくなる道、SREを埋め込んだDeveloper Platform / tech drivers day8
chmikata
4
620
Claude Codeから見る、エンジニアの世界の変容とその先
oikon48
4
2k
VLA-JEPA: Enhancing Vision-Language-Action Models with Latent World Models
takmin
0
300
構造で守らせる データ・法務・セキュリティ・開発チームとつくる AI時代のデータガバナンスとデータ基盤のリアル
legalontechnologies
PRO
0
220
How we choose session proposals
kawaguti
PRO
0
110
日本AIベンチャーレポート2026
kentarofujii
0
220
Draft AIエージェントの トークン消費を最小化する 8つの原則
kinopeee
5
1.6k
QAエンジニアがSoutherを使ってみたの〜10分でわかるSouther〜
mhlyc
0
110
「作れる」と「リリースできる」の間にあったもの── PdMを外して見えた、PdMがやるべき仕事/Buildable ≠ Shippable: What Removing the PM Taught Me About the PM’s Job
yappli_developers
0
230
フィンテック養成勉強会#68
finengine
0
240
データマネジメント × 法務で作りあげる、 freeeの新しいデータガバナンスへの軌跡
freee
PRO
0
140
Featured
See All Featured
Leo the Paperboy
mayatellez
10
2.4k
StorybookのUI Testing Handbookを読んだ
zakiyama
31
7k
The World Runs on Bad Software
bkeepers
PRO
72
12k
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
inesmontani
PRO
3
3.8k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
37
6.6k
The Language of Interfaces
destraynor
162
27k
Are puppies a ranking factor?
jonoalderson
2
4.1k
BBQ
matthewcrist
90
10k
Efficient Content Optimization with Google Search Console & Apps Script
katarinadahlin
PRO
1
940
Designing for humans not robots
tammielis
254
26k
Digital Ethics as a Driver of Design Innovation
axbom
PRO
1
460
Stop Working from a Prison Cell
hatefulcrawdad
274
21k
Transcript
Ԭٕज़Պֶେֶࣗવݴޠॲཧݚڀࣨ ੁ३ࢤ จݙհ ݄ .BSFL3FJ )FMFO:BOOBLPVEBLJT 1SPDFFEJOHTPGUIFUI8PSLTIPQPO*OOPWBUJWF6TFPG/-1GPS #VJMEJOH&EVDBUJPOBM"QQMJDBUJPOT QBHFTr$PQFOIBHFO
%FONBSL 4FQUFNCFS "VYJMJBSZ0CKFDUJWFT GPS/FVSBM&SSPS%FUFDUJPO.PEFMT
"CTUSBDU w ݴޠֶशऀͷ࡞ͨ͠จͷޡΓݕग़ w χϡʔϥϧΛ༻͍ͨܥྻϥϕϦϯάख๏ʹ͓͍ͯɺ ิॿతͷ܇࿅ͷ༗༻ੑΛݕূ w ҎલͷޡΓݕγεςϜͱಉ͡ͷύϥϝʔλͰ ΑΓྑ͍ύϑΥʔϚϯεΛୡ !2
*OUSPEVDUJPO w ݴޠֶशऀͷ࡞ͨ͠จͰ༷ʑͳλΠϓͷޡΓΛ ࣝผ͢Δඞཁ͕͋Δ ɾػೳޠͷޡͬͨ༻ ɾ༰ޠͷҙຯతͳޡΓʢલஔࢺɾܗ༰ࢺͷΈ߹ΘͤͳͲʣ w ݴޠͷΑΓྑ͍දݱΛֶͼɺจ຺ʹ͓͚ΔޡΓΛ ΑΓਖ਼֬ʹݕग़Ͱ͖ΔγεςϜΛߏங͢Δ w
ਖ਼൱ͷ༧ଌ͚ͩͰͳ͘طଘͷσʔλ͔Βநग़Ͱ͖Δ ใΛ༧ଌ͢Δ͜ͱΛࢼΈΔ !3
"VYJMJBSZ-PTT'VODUJPOT !4 xt h( f ) t h(b) t dt
yt DPSSFDUJODPSSFDU 8PSE yt,k : MBCFMLΛ࣋ͭτʔΫϯUͷ༧ଌ֬ ˜ yt,k : ̍τʔΫϯUͷਖ਼͍͠ϥϕϧ͕Lͷ࣌ ̌ͦΕҎ֎ͷ߹
"VYJMJBSZ-PTT'VODUJPOT !5 xt y(1) t y(2) t d(1) t d(2)
t h( f ) t h(b) t DPSSFDUJODPSSFDU 8PSE ผͷλεΫ yt,k : MBCFMLΛ࣋ͭτʔΫϯUͷ༧ଌ֬ ˜ yt,k : ̍τʔΫϯUͷਖ਼͍͠ϥϕϧ͕Lͷ࣌ ̌ͦΕҎ֎ͷ߹
"VYJMJBSZ-PTT'VODUJPOT w GSFRVFODZ ୯ޠͷසΛ༧ଌ͢Δ w FSSPSUZQF ୯ޠͷޡΓͷछྨΛ༧ଌ͢Δ w pSTUMBOHVBHF ֶशऀͷୈҰݴޠΛ༧ଌ͢Δ
w QBSUPGTQFFDI ୯ޠͷࢺΛ༧ଌ͢Δ w HSBNNBUJDBMSFMBUJPOT ୯ޠؒͷґଘؔΛ༧ଌ͢Δ ɹ !6 ผͷλεΫ
"VYJMJBSZ-PTT'VODUJPOT !7
&WBMVBUJPOTFUVQBOEEBUBTFUT w #BTFMJOFɿ3FJBOE:BOOBLPVEBLJT ɾ#J-45.Λ༻͍ͯ4P5"Λୡͨ͠Ϟσϧ w %BUBTFUT ɾ'JSTU$FSUJpDBUFJO&OHMJTI '$&
EBUBTFU ɾ$P/--TIBSFEUBTLUFTUTFU !8
&WBMVBUJPOTFUVQBOEEBUBTFUT w ύϥϝʔλ ɾXPSEFNCFEEJOHTTJ[F ɾJOJUJBMJ[FE QVCMJDMZBWBJMBCMFXPSEWFD .JLPMPWFUBM ɹFNCFEEJOHTUSBJOFEPO(PPHMF/FXT
ɾ-45.IJEEFOMBZFST ɾUBTLTQFDJpDIJEEFOMBZFST ɾPQUJNJ[FE"EBEFMUB ;FJMFS !9
!10
"MUFSOBUJWF5SBJOJOH4USBUFHJFT w ϚϧνλεΫֶशʹؔ͢Δݚڀ ෳͷσʔληοτͰಉ͡γεςϜΛ࠷దԽ͢Δ͜ͱʹ ॏΛஔ͍͍ͯΔ w ༗༻ੑΛࣔͨ͢Ίɺ࣍ͷσʔληοτΛ༻͍ͯ܇࿅ ɾ$P/--EBUBTFUʢDIVOLJOHʣ ɹɹ 5KPOH,JN4BOHBOE#VDIIPM[
ɾ$P/--DPSQVTʢ/&3ʣ ɹɹ 5KPOH,JN4BOHBOE%F.FVMEFS ɾ1FOO5SFFCBOL 15# 104DPSQVT ɹɹ .BSDVTFUBM !11
"MUFSOBUJWF5SBJOJOH4USBUFHJFT w ࣍ͷͭͷํ๏Ͱ܇࿅͢Δ ผͷλεΫͷσʔληοτͰ܇࿅ͨ͋͠ͱɺ ޡΓݕग़σʔληοτͰ܇࿅ ผͷλεΫͷσʔληοτͱޡΓݕग़ͷ σʔληοτΛަޓʹ܇࿅ !12
"MUFSOBUJWF5SBJOJOH4USBUFHJFT !13
"MUFSOBUJWF5SBJOJOH4USBUFHJFT !14
"EEJUJPOBM5SBJOJOH%BUB w NVMUJUBTLMFBSOJOH ར༻ՄೳͳλεΫݻ༗ͷ܇࿅σʔλ͕গͳ͍࣌ʹޮՌ͕ ظ͞ΕΔ w େنͳσʔληοτΛ༻͍ͨ߹ͷޮՌΛݕূ !15
"EEJUJPOBM5SBJOJOH%BUB w ࣍ͷσʔληοτΛ༻ʢ߹ܭ.UPLFOTʣ ɾ$BNCSJEHF-FBSOFS$PSQVT $-$ /JDIPMMT ɾ/64$PSQVTPG-FBSOFS&OHMJTI /6$-& %BIMNFJFSFUBM
ɾ-BOHDPSQVT .J[VNPUPFUBM w܇࿅࣌ʹֶश͢ΔλεΫ ɾ&SSPS%FUFDU ɾ104UBHHJOH !16
"EEJUJPOBM5SBJOJOH%BUB !17
$PODMVTJPO w ݴޠֶशऀͷ࡞ͨ͠จͷޡΓݕΛվળ͢ΔͨΊʹ χϡʔϥϧܥྻϥϕϦϯάʹิॿతͳଛࣦؔΛ౷߹ w 104λάɺจ๏తؔɺޡΓͷछྨ͕ޡΓݕग़ʹ༗༻Ͱ Έ߹ΘͤΔ͜ͱͰ݁Ռ͕վળ w ར༻Մೳͳ܇࿅σʔλ͕ݶΒΕ͍ͯΔ͚࣌ͩͰͳ͘ ଟ͘ͷ܇࿅σʔλΛ༻ͨ͠߹Ͱ༗ޮ
!18