Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
文献紹介: Confidence Modeling for Neural Semantic P...
Search
Yumeto Inaoka
October 24, 2018
Research
3
230
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
Tweet
Share
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
190
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
240
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
160
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
180
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
160
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
280
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
350
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
230
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
230
Other Decks in Research
See All in Research
CVPR2025論文紹介:Unboxed
murakawatakuya
0
180
EOGS: Gaussian Splatting for Efficient Satellite Image Photogrammetry
satai
4
670
MIRU2025 チュートリアル講演「ロボット基盤モデルの最前線」
haraduka
15
8.9k
日本語新聞記事を用いた大規模言語モデルの暗記定量化 / LLMC2025
upura
0
250
不確実性下における目的と手段の統合的探索に向けた連続腕バンディットの応用 / iot70_gp_rff_mab
monochromegane
2
190
Creation and environmental applications of 15-year daily inundation and vegetation maps for Siberia by integrating satellite and meteorological datasets
satai
3
400
財務諸表監査のための逐次検定
masakat0
0
150
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
770
Adaptive Experimental Design for Efficient Average Treatment Effect Estimation and Treatment Choice
masakat0
0
120
Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation
satai
3
230
HoliTracer:Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery
satai
3
120
Google Agent Development Kit (ADK) 入門 🚀
mickey_kubo
2
2.1k
Featured
See All Featured
Bash Introduction
62gerente
615
210k
Into the Great Unknown - MozCon
thekraken
40
2.1k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.1k
Code Review Best Practice
trishagee
72
19k
Done Done
chrislema
185
16k
Producing Creativity
orderedlist
PRO
347
40k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
55
3k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
140
34k
Making Projects Easy
brettharned
120
6.4k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
9.7k
Code Reviewing Like a Champion
maltzj
526
40k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
10
870
Transcript
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