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
230
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
170
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
340
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
業界横断 副業・兼業者の実態調査
fkske
0
230
Vision and LanguageからのEmbodied AIとAI for Science
yushiku
PRO
1
510
「どう育てるか」より「どう働きたいか」〜スクラムマスターの最初の一歩〜
hirakawa51
0
830
SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images
satai
3
120
とあるSREの博士「過程」 / A Certain SRE’s Ph.D. Journey
yuukit
9
4.1k
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
150
引力・斥力を制御可能なランダム部分集合の確率分布
wasyro
0
230
心理言語学の視点から再考する言語モデルの学習過程
chemical_tree
2
550
AI エージェントを活用した研究再現性の自動定量評価 / scisci2025
upura
1
140
電力システム最適化入門
mickey_kubo
1
870
2021年度-基盤研究B-研究計画調書
trycycle
PRO
0
240
AIによる画像認識技術の進化 -25年の技術変遷を振り返る-
hf149
7
3.9k
Featured
See All Featured
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
The Cult of Friendly URLs
andyhume
79
6.6k
Automating Front-end Workflow
addyosmani
1370
200k
Documentation Writing (for coders)
carmenintech
73
5k
Product Roadmaps are Hard
iamctodd
PRO
54
11k
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
656
61k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
A designer walks into a library…
pauljervisheath
207
24k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
53
2.9k
The Art of Programming - Codeland 2020
erikaheidi
55
13k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
185
54k
Raft: Consensus for Rubyists
vanstee
140
7.1k
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