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
Dynamic Multi-Level Multi-Task Learning for Sen...
Search
onizuka laboratory
October 17, 2018
Research
59
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Dynamic Multi-Level Multi-Task Learning for Sentence Simplification
弊研究室で行なったCOLING2018読み会の発表資料です。
onizuka laboratory
October 17, 2018
More Decks by onizuka laboratory
See All by onizuka laboratory
Phrase-Based & Neural Unsupervised Machine Translation
onilab
0
130
Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions
onilab
0
100
Card-660: A Reliable Evaluation Framework for Rare Word Representation Models
onilab
0
47
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
onilab
0
160
Integrating Transformer and Paraphrase Rules for Sentence Simplification
onilab
0
72
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
onilab
0
70
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
onilab
0
110
Modeling Multi-turn Conversation with Deep Utterance Aggregation
onilab
0
100
Learning Semantic Sentence Embeddings using Pair-wise Discriminator
onilab
0
130
Other Decks in Research
See All in Research
Vector Map as Language: Toward Unified Remote Sensing Vector Mapping
satai
3
320
論文読み会 SNLP2026 Tau2-Bench: Evaluating Conversational Agents in a Dual-Control Environment
s_mizuki_nlp
0
300
湯村研究室の紹介2026 / yumulab2026
yumulab
0
130
CVPR2026論文紹介_VLMにとって良いvision encoderとは何か?Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance
kobayashi31
1
270
第64回CV・PRML勉強会 論文紹介:Linguistic Priors for Visual Decoupling: Towards Symmetric Vision-Brain Alignment
sokikatayama
0
250
Kaggle|AI Agent Security — しくじり先生、俺みたいになるな
pomcho555
1
120
横浜市長(山中氏)の言動にかかる第三者による調査報告書
sishi2026
0
640
[最先端NLP勉強会2026] Checklists Are Better Than Reward Models For Aligning Language Models
nzw0301
1
330
GLIM とMegaParticles:正規分布近似の限界とタイトカップリング&パーティクルフィルタの進展 / GLIM and MegaParticles : Progress of the distribution representation in SLAM
koide3
0
960
敵対生成プロンプト同時探索による内省型プロンプト最適化
kinoue_smarthr
0
440
生成AIなんでも展示会vol6 LT登壇資料 NexteraBERT
rikkabotan7
0
190
[最先端NLP勉強会2026] Agentic Rubrics as Contextual Verifiers for SWE Agents
rfujii
1
390
Featured
See All Featured
The Cost Of JavaScript in 2023
addyosmani
55
10k
Principles of Awesome APIs and How to Build Them.
keavy
128
18k
Lightning Talk: Beautiful Slides for Beginners
inesmontani
PRO
2
730
The Spectacular Lies of Maps
axbom
PRO
1
1.1k
Mozcon NYC 2025: Stop Losing SEO Traffic
samtorres
1
580
Imperfection Machines: The Place of Print at Facebook
scottboms
270
14k
The World Runs on Bad Software
bkeepers
PRO
72
12k
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
mfonobong
2
590
How to make the Groovebox
asonas
2
2.5k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
Beyond borders and beyond the search box: How to win the global "messy middle" with AI-driven SEO
davidcarrasco
3
280
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
63
46k
Transcript
$ )BO(VP 3BNBLBOUI 1BTVOVSV .PIJU #BOTBM %ZOBNJD.VMUJ-FWFM.VMUJ5BTL -FBSOJOHGPS4FOUFODF 4JNQMJGJDBUJPO
#ݪ େو $0-*/(ಡΈձʢʣ
࣍ l ֓ཁ l Ϟσϧ l ධՁํ๏ l ݁Ռ l
"CMBUJPOT"OBMZTJT
֓ཁ จͷฏқԽ l ׂɺআɺݴ͍͑ͳͲͰɺՄಡੑΛ্͛Δ l ༗ޮͳೖྗจཧతʹؚΊΔ͖ʢؚҙʣ #BTFMJOF l ϙΠϯλίϐʔϝΧχζϜͷTFRTFR
֓ཁ ఏҊख๏ l ϚϧνλεΫɾϚϧνϨϕϧ֊ ◦ ิॿλεΫʢؚҙɾݴ͍͑ʣ͕ɺҟͳΔϨϕϧͷ֊ l λεΫͷΓସ͑ํΛಈతʹֶश ◦ ଟόϯσΟοτϕʔεͷ܇࿅ख๏
ධՁɾੳ l ࣗಈධՁʢ4"3*ɺ',(-ʣͱखಈධՁͰ༏Εͨ
࣍ l ֓ཁ l Ϟσϧ l ධՁํ๏ l ݁Ռ l
"CMBUJPOT"OBMZTJT Ø Baseline Ø Ø Ø Ø Ø
Ϟσϧɿ#BTFMJOF ϙΠϯλίϐʔจฏқԽϞσϧ l ҎԼͷΛඋ͑ͨTFRTFRϞσϧ ◦ Ξςϯγϣϯʢ#BIEBOBV FUBM ʣ ◦ ϙΠϯλίϐʔϝΧχζϜʢ4FFFUBM
ʣ
Ϟσϧɿ#BTFMJOF Ξςϯγϣϯ 4FFFUBM l(FU5P5IF1PJOU4VNNBSJ[BUJPOXJUI1PJOUFS(FOFSBUPS/FUXPSLTz BS9JWF
Ϟσϧɿ#BTFMJOF ϙΠϯλίϐʔϝΧχζϜ 4FFFUBM l(FU5P5IF1PJOU4VNNBSJ[BUJPOXJUI1PJOUFS(FOFSBUPS/FUXPSLTz BS9JWF
ϞσϧɿิॿλεΫ̍ ؚҙੜλεΫ l ฏқจೖྗʹै͏͖ l ҙຯతʢߴʣ l ؚҙੜϞσϧ܇࿅༻σʔληοτ ◦ 4/-*
#PXNBOFUBM ◦ .VMUJ/-* 8JMMJBNTFUBM
ϞσϧɿิॿλεΫ̎ ݴ͍͑ੜλεΫ l ߏจޠኮͰɺฒସ͑ॻ͖͑ l ޠኮ౷ޠʢʣ l ݴ͍͑ੜλεΫ༻܇࿅σʔληοτ ◦ 1BSB/.5
8JFUJOH BOE(JNQFM B
ϞσϧɿϚϧνλεΫϞσϧ
ϞσϧɿϚϧνλεΫֶश TFRTFRͰ l Τϯίʔμσίʔμͷɺύϥϝʔλڞ༗ ఏҊख๏ l ڞ༗ͰɺύϥϝʔλͷҰ෦Λඇެ։ɺ Γʢؔ࿈දݱʣΛڞ༗ l ڞ༗ύϥϝʔλΛଛࣦؔͷϖφϧςΟ߲Ͱɺ
͋Δڑࢦඪʹ͚ۙͮΔ
ϞσϧɿϚϧνϨϕϧڞ༗ TFRTFRͷ֤֊ͰҟͳΔػೳΛͭ l #FMJOLPW FUBM l ʢೖྗଆʣʹ୯ޠߏΛֶशʢݴ͍͑ʣ l ߴʹҙຯʹযΛ߹ΘͤΔʢؚҙʣ
Ϟσϧɿιϑτڞ༗ ϋʔυڞ༗ l ڞ༗͢ΔύϥϝʔλΛ݁ͼ͚ͭΔ ιϑτڞ༗ l ҟͳΔλεΫ͕ɺύϥϝʔλۭؒͷͲͷ෦Λڞ༗͢Δ ͔બͰ͖Δ l ଛࣦؔ
! " = −log () * +; " + . "/ − 0/ ◦ " ओλεΫʢฏқԽʣͷશͯͷύϥϝʔλ ◦ "/ 0/ ओλεΫͱิॿλεΫͷڞ༗ύϥϝʔλͷαϒηοτ
ϞσϧɿϚϧνλεΫ܇࿅ طଘख๏ l ʢ੩తͳʣࠞ߹ൺ !"" : !$% : !&& ◦
ओλεΫʢฏқԽʣɿؚҙɿݴ͍͑ ఏҊख๏ l ੩తͰͳ͘ಈతʹ܇࿅͍ͨ͠
Ϟσϧɿಈతࠞ߹ൺֶश ଟόϯσΟοτ l XJUI#PMU[NBOOFYQMPSBUJPO ,BFMCMJOH FUBM l XJUIࢦҠಈฏۉߋ৽ϧʔϧ
Ϟσϧɿಈతࠞ߹ൺֶश ଟόϯσΟοτ
Ϟσϧɿಈతࠞ߹ൺֶश ଟόϯσΟοτ l ̏λεΫͷઃఆͷू߹ !" , ⋯ , !% l
֤ &' ͰɺΛબ͠ɺใु ()* ΛಘΔ ◦ ใुɺओλεΫͷෛͷ WBMJEBUJPOMPTT l όϯσΟοτίϯτϩʔϥͷํ l ֤ &' Ͱͷ֤ + ͷߦಈਪఆ
࣍ l ֓ཁ l Ϟσϧ l ධՁํ๏ l ݁Ռ l
"CMBUJPOT"OBMZTJT
ධՁํ๏ɿσʔληοτ 5SBJO 7BMJE 5FTU /FXTFMB 4NBMM8JLJ
-BSHF8JLJ 4/-* .VMUJ/-* ؚҙੜ༻ ʢ߹Θͤͯʣ 8JFUJOH(JNQFM ݴ͍͑༻ . ʢ߹Θͤͯʣ,
ධՁํ๏ɿධՁࢦඪ ࣗಈධՁ l 4"3* l ',(- ◦ ͍จΛධՁ͕ͪ͠ʢ4IBSEMPX ʣ l
#-&6 ◦ ฏқԽͰؔ࿈ੑ͕͍ʢ;IVFUBM ଞʣ ◦ มߋ͠ͳ͍อकతͳγεςϜ͕ධՁ͞Ε͕ͪʢಉ্ʣ
ධՁํ๏ɿධՁࢦඪ खಈධՁ l ྲྀெੑʢ'MVFODZʣ ◦ JTUIFPVUQVUHSBNNBUJDBMBOEXFMMGPSNFE l ଥੑʢ"EFRVBDZʣ ◦ UPXIBUFYUFOUJTUIFNFBOJOHFYQSFTTFEJOUIFPSJHJOBM
TFOUFODFQSFTFSWFEJOUIFPVUQVU l ฏқੑʢ4JNQMJDJUZʣ ◦ JTUIFPVUQVUTJNQMFSUIBOUIFPSJHJOBMTFOUFODF
࣍ l ֓ཁ l Ϟσϧ l ධՁํ๏ l ݁Ռ l
"CMBUJPOT"OBMZTJT
݁Ռ l #BTFMJOFWTطଘख๏ ◦ /FXTFMB Ͱ ',(-༏উɺ4"3*࣍ ◦ 8JLJͰಉ
݁Ռ l #BTFMJOF &OU1BSWT#BTFMJOFطଘख๏ ◦ /FXTFMB ͷ ',(-ͱ 4"3*Ͱ༏উ l
#BTFMJOF &OU 1BSWT#BTFMJOF &OU1BS ◦ /FXTFMB 8JLJͰ ',(- 4"3*͍͍ͩͨ༏উ
݁Ռ l ʢิॿλεΫͷʣࠞ߹ൺʢಈతWT੩తʣ ◦ /FXTFMB ͱ 8JLJ4NBMM Ͱ 4"3* ༏উ
݁Ռ ਓखධՁ l XBZWTଞ ◦ ฏқੑʢ4JNQMJDJUZʣͰ༏উ ◦ ଥੑʢ"EFRVBDZʣ %3&44-4 ʹෛ͚ͨˠฏқԽॏࢹ
◦ ฏۉείΞɺ%3&44-4ΑΓྑ͍
݁Ռ ೖग़ྗͷҰக l XBZ͍ʢ (SPVOEUSVUIʹ͍ۙʣ l %3&44-4 ߴ͍ ◦ ଥੑʢ"EFRVBDZʣ͕ߴ͔ͬͨͷᰐ͚Δ
࣍ l ֓ཁ l Ϟσϧ l ධՁํ๏ l ݁Ռ l
"CMBUJPOT"OBMZTJT
"CMBUJPOT"OBMZTJT ଞͷڞ༗ख๏ʁ l ʴߴ͕༏উ
"CMBUJPOT"OBMZTJT ڞ༗ʢιϑτ WTϋʔυʣʁ l ιϑτ͕ 4"3*ڧ͍
"CMBUJPOT"OBMZTJT 4"3*ͷৄࡉ l XBZ༏উ
"CMBUJPOT"OBMZTJT ̎ͭͷଟόϯσΟοτख๏ l ͭɿ࠷ޙΛهͯࠞ͠߹ൺΛݻఆ͢Δ l 4"3*ʢ̍ͭʣWT ʢ̎ͭʣ
"CMBUJPOT"OBMZTJT ̎ͭͷଟόϯσΟοτख๏
"CMBUJPOT"OBMZTJT ϚϧνλεΫֶश WTσʔλ֦ு l ຊʹɺิॿλεΫͷzػೳz͕ੑೳ্ͤͨ͞ʁ ◦ ิॿλεΫ༻ͷlσʔλՃzͷӨڹͰͳ͍ʁ l ิॿλεΫ༻σʔλʢ4/-* .VMUJ/-*
ͱ 1BSB/.5ʣΛɺݸผʹ FNCFEEJOHͯ͠ ओλεΫϞσϧʹΈࠐΜͩ l ఏҊख๏͕େ෯ʹ༏Ε͍ͯͨ
"CMBUJPOT"OBMZTJT ྫ