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: Confidence Modeling for Neural Semantic P...
Search
Yumeto Inaoka
October 24, 2018
Research
260
3
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
文献紹介: Confidence Modeling for Neural Semantic Parsing
2018/10/24の文献紹介で発表
Yumeto Inaoka
October 24, 2018
Transcript
23 slides
Confidence Modeling for Neural Semantic Parsing จݙհɹ Ԭٕज़Պֶେֶɹࣗવݴޠॲཧݚڀࣨ ҴԬɹເਓ
Literature Confidence Modeling for Neural Semantic Parsing Li Dong† and
Chris Quirk‡ and Mirella Lapata† †School of Informatics, University of Edinburgh ‡Microsoft Research, Redmond Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers), pages 743–753, 2018. !2
Abstract • Neural Semantic Parsing (seq2seq) ʹ͓͚Δ֬৴ϞσϦϯά • ೖྗͷͲ͕͜ෆ͔֬͞ͷཁҼʹͳ͍ͬͯΔ͔Λࣝผ •
ࣄޙ֬ɺΞςϯγϣϯʹґଘ͢Δख๏ΑΓ༏ल !3
Introduction • Neural Semantic ParsingظͰ͖Δ݁ՌΛग़͢ҰํͰ ग़ྗͷݪҼ͕ղऍͮ͠Β͍ϒϥοΫϘοΫεͱͯ͠ಈ࡞ • Ϟσϧͷ༧ଌʹର͢Δ֬৴ͷਪఆʹΑͬͯ༗ҙٛͳ ϑΟʔυόοΫ͕ՄೳʹͳΔͷͰͳ͍͔ •
֬৴ͷείΞϦϯάख๏ࣄޙ֬ p(y|x) ͕Α͘༻͞ΕΔ → ઢܗϞσϧͰ༗ޮ͕ͩχϡʔϥϧϞσϧͰྑ͘ͳ͍ !4
Neural Semantic Parsing • In: Natural Language Out: Logical form
• Seq2seq with LSTM • Attention mechanism • Maximize the likelihood • Beam Search !5 !5
Confidence Estimation • ೖྗqͱ༧ଌͨ͠ҙຯදݱa͔Β֬৴s(q, a) ∈ (0, 1)Λ༧ଌ • ֬৴ͷஅʹʮԿΛΒͳ͍͔ʯΛਪఆ͢Δඞཁ͕͋Δ
• Ϟσϧͷෆ͔֬͞ɺσʔλͷෆ͔֬͞ɺೖྗͷෆ͔֬͞Λجʹ ࡞ΒΕΔࢦඪ͔Β֬৴ΛճؼϞσϧʹΑͬͯٻΊΔ !6
Model Uncertainty • ϞσϧͷύϥϝʔλߏʹΑΔෆ͔֬͞Ͱ֬৴͕Լ ← ྫ͑܇࿅σʔλʹؚ·ΕΔϊΠζ֬తֶशΞϧΰϦζϜ • Dropout Perturbation, Gaussian
Noise, Posterior Probability͔Β ࢦඪΛ࡞͠ɺෆ͔֬͞Λ༧ଌ !7
Dropout Perturbation • DropoutΛςετ࣌ʹ༻ (ਤதͷi, ii, iii, ivͷՕॴ) • จϨϕϧͰͷࢦඪɿ
• τʔΫϯϨϕϧͰͷࢦඪɿ • ɹɹઁಈͤ͞Δύϥϝʔλɹ݁ՌΛूΊͯࢄΛܭࢉ !8
Gaussian Noise • Gaussian NoiseΛϕΫτϧՃ͑ͯDropoutͱಉ༷ʹࢄΛܭࢉ ← DropoutϕϧψʔΠɺ͜ΕΨεʹै͏ϊΠζ • ϊΠζͷՃ͑ํҎԼͷ2ͭ (vݩͷϕΫτϧ,
gGaussian Noise) !9
Posterior Probability • ࣄޙ֬ p(a | q)ΛจϨϕϧͰͷࢦඪʹ༻ • τʔΫϯϨϕϧͰҎԼͷ2ͭΛࢦඪʹ༻ •
ɹɹɹɹɹɹɹɹɹɹɹɹɿ࠷ෆ͔֬ͳ୯ޠʹண • ɹɹɹɹɹɹɹɹɹɹɹɹɹɹɿτʔΫϯຖͷperplexity !10
Data Uncertainty • ܇࿅σʔλͷΧόϨοδෆ͔֬͞ʹӨڹΛ༩͑Δ • ܇࿅σʔλͰݴޠϞσϧΛֶशͤ͞ɺೖྗͷݴޠϞσϧ֬Λ ࢦඪʹ༻͍Δ • ೖྗͷະޠτʔΫϯΛࢦඪʹ༻͍Δ !11
Input Uncertainty • Ϟσϧ͕ᘳͰೖྗ͕ᐆດͩͱෆ͔֬͞ൃੜ͢Δ (e.g. 9 o’clock -> flight_time(9am) or
flight_time(9pm) ) • ্Ґީิͷ֬ͷࢄΛ༻͍Δ • ΤϯτϩϐʔΛ༻͍Δ ← a’αϯϓϦϯάۙࣅ !12
Confidence Storing • ͜ΕΒͷ༷ʑͳࢦඪΛ༻͍ͯ֬৴ͷείΞϦϯάΛߦ͏ • ޯϒʔεςΟϯάϞσϧʹ֤ࢦඪΛ༩ֶ͑ͯशͤ͞Δ ग़ྗ͕0ʙ1ʹͳΔΑ͏ϩδεςΟοΫؔͰϥοϓ • ޯϒʔεςΟϯάϞσϧҎԼͷղઆهࣄ͕͔Γ͍͢ (ʮGradient
Boosting ͱ XGBoostʯ: ɹ https://zaburo-ch.github.io/post/xgboost/ ) !13
Uncertainty Interpretation • Ͳͷೖྗ͕ෆ͔֬͞ʹ࡞༻͍ͯ͠Δ͔Λಛఆ → ͦͷೖྗΛಛผͳέʔεͱͯ͠ѻ͏͕ग़དྷΔ • ༧ଌ͔ΒೖྗτʔΫϯؒ·ͰΛٯൖ → ֤τʔΫϯͷෆ͔֬͞ͷد༩͕Θ͔Δ
!14
Experiments (Datasets) • IFTTT σʔληοτ (train-dev-test : 77,495 - 5,171
- 4,294) • DJANGO σʔληοτ (train-dev-test : 16,000 - 1,000 - 1,805) !15
Experiments (Settings) • Dropout Perturbation Dropout rate0.1ɺ30ճ࣮ߦͯ͠ࢄΛܭࢉ • Gaussian Noise
ඪ४ภࠩΛ0.05ʹઃఆ • Probability of Input ݴޠϞσϧͱͯ͠KenLMΛ༻ • Input Uncertainty 10-best ͷީิ͔ΒࢄΛܭࢉ !16
Experiments (Results) • Model Uncertainty͕࠷ޮՌత • Data UncertaintyӨڹ͕খ͍͞ → In-domainͰ͋ΔͨΊ
!17
Experiments (Results) !18
Experiments (Results) • Model Uncertaintyͷ ࢦඪ͕ॏཁ • ಛʹIFTTT#UNKͱ Var͕ॏཁ !19
Experiments (Results) !20
Experiments (Results) • ϊΠζΛՃ͑ͨτʔΫϯྻͱ ٯൖͰಘͨτʔΫϯྻͷ ΦʔόʔϥοϓͰධՁ • Attentionͱൺֱͯ͠ߴ͍ • K=4ʹ͓͍ͯ80%͕Ұக
!21
Experiments (Results) !22
Conclusions • Neural Semantic ParsingͷͨΊͷ֬৴ਪఆϞσϧΛఏࣔ • ෆ͔֬͞ΛೖྗτʔΫϯϨϕϧͰղऍ͢Δํ๏Λఏࣔ • IFTTT, DJANGOσʔληοτʹ͓͍ͯ༗ޮੑΛ֬ೝ
• ఏҊϞσϧSeq2seqΛ࠾༻͢Δ༷ʑͳλεΫͰద༻Մೳ • Neural Semantic ParsingͷActive Learningʹ͓͍ͯར༻Ͱ͖Δ !23
More Decks by Yumeto Inaoka
See All by Yumeto Inaoka
文献紹介: Quantity doesn’t buy quality syntax with neural language models
yumeto
1
230
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
300
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
200
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
220
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
250
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
340
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
440
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
260
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
310
Other Decks in Research
See All in Research
オンライン凸最適化の基礎とゲーム理論への応用 (IBIS 2026 チュートリアル)
taira_tsuchiya
2
1.4k
生成AIなんでも展示会vol6 LT登壇資料 NexteraBERT
rikkabotan7
0
220
最先端NLP 2026 論文紹介: Wait, Wait, Wait... Why Do Reasoning Models Loop? / SNLP Paper Review: Wait, Wait, Wait... Why Do Reasoning Models Loop?
tkng
0
280
就労支援の現場での生成AI活用
enochan
0
220
超効率化への挑戦:1bit LLMの現状と展望
yumaichikawa
1
1k
AI対話に何を挟むか ― 高回転対話・デジタル摘録・手書き記録による創造体験の違い|日本創造学会2026
ishiirikie
0
210
[IEICE-Soceity-Conf2026] セマンティック通信を見据えたマルチスケールセンシングと 学習の融合によるデジタルツイン基盤 / Digital Twin Infrastructure via the Fusion of Multi-Scale Sensing and Learning toward Semantic Communications
pman0214
0
150
Kaggle|AI Agent Security — しくじり先生、俺みたいになるな
pomcho555
1
140
A Preliminary Performance Evaluation of Cassandra Accord
sira
0
110
【令和7年度版】内航船 VS 外航船 早見表
anikisencyo
0
220
Santé et fertilité des sols : ce que nous disent les pratiques dans les systèmes de polyculture-élevage
institutdelelevage
PRO
0
240
[Research Paper Analysis] Deep Learning - SigLIP2
auranightsky
0
170
Featured
See All Featured
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
52
6.2k
Speed Design
sergeychernyshev
33
2.2k
Why Mistakes Are the Best Teachers: Turning Failure into a Pathway for Growth
auna
0
360
The Mindset for Success: Future Career Progression
greggifford
PRO
0
560
How to Grow Your eCommerce with AI & Automation
katarinadahlin
PRO
2
350
The SEO identity crisis: Don't let AI make you average
varn
0
630
Docker and Python
trallard
47
4.3k
A designer walks into a library…
pauljervisheath
211
25k
The browser strikes back
jonoalderson
0
2k
The Curse of the Amulet
leimatthew05
4
17k
Unlocking the hidden potential of vector embeddings in international SEO
frankvandijk
0
1k
16th Malabo Montpellier Forum Presentation
akademiya2063
PRO
0
470