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
文脈の解析
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Yumeto Inaoka
March 09, 2017
Technology
300
0
Share
文脈の解析
2017/03/09のB3ゼミで発表
Yumeto Inaoka
March 09, 2017
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
210
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
270
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
190
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
200
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
190
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
320
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
390
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
250
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
270
Other Decks in Technology
See All in Technology
古今東西SRE
okaru
1
130
Percolatorを廃止し、マルチ検索サービスへ刷新した話 / Search Engineering Tech Talk 2026 Spring
visional_engineering_and_design
0
330
変化の激しい時代をゴキゲンに生き抜くために 〜ストレスマネジメントのススメ〜
kakehashi
PRO
4
1.1k
Oracle Cloud Infrastructure presents managed, serverless MCP Servers for Oracle AI Database
thatjeffsmith
0
110
Oracle Exadata Database Service on Cloud@Customer X11M (ExaDB-C@C) サービス概要
oracle4engineer
PRO
2
8k
AIが盛んな時代に 技術記事を書き始めて起きた私の中での小さな変化
peintangos
0
360
AIと乗り切った1,500ページ超のヘルプサイト基盤刷新とさらにその先の話
mugi_uno
2
310
Digital Independence: Why, When and How
wannesrams
0
300
ファインディの事業拡大を支える 拡張可能なデータ基盤へのリアーキテクチャ
hiracky16
0
930
エンタープライズの厳格な制約を開発者に意識させない:クラウドネイティブ開発基盤設計/cloudnative-kaigi-golden-path
mhrtech
0
340
サンプリングは「作る」のか「使う」のか? 分散トレースのコストと運用を両立する実践的戦略 / Why you need the tail sampling and why you don't want it
ymotongpoo
3
120
雑談は、センサーだった
bitkey
PRO
2
210
Featured
See All Featured
Understanding Cognitive Biases in Performance Measurement
bluesmoon
32
2.9k
Designing Powerful Visuals for Engaging Learning
tmiket
1
360
SEO in 2025: How to Prepare for the Future of Search
ipullrank
3
3.4k
GraphQLの誤解/rethinking-graphql
sonatard
75
12k
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.5k
30 Presentation Tips
portentint
PRO
1
290
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
38
2.8k
Effective software design: The role of men in debugging patriarchy in IT @ Voxxed Days AMS
baasie
0
340
Building a A Zero-Code AI SEO Workflow
portentint
PRO
0
490
sira's awesome portfolio website redesign presentation
elsirapls
0
230
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
2
3.9k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Transcript
จ຺ͷղੳ #θϛ ࣗવݴޠॲཧݚڀࣨɹҴԬເਓ
ࢀߟʹͨ͠ॻ੶
ൃද༰ ˗ จ຺ ˗ ڞࢀরͱরԠ ˗ લํরԠͱޙํরԠ ˗ จ຺রԠͱ֎քরԠ ˗
θϩরԠ ˗ রԠղੳͱθϩরԠղੳ
จ຺ ˗ จ຺ɹɿจͷͭͳ͕Γ۩߹ ˗ ݁ଋੑɿಉ͡Α͏ͳࣄ͕จষʹݱΕΔ ˗ Ұ؏ੑɿจಉ͕࢜ҙຯؔΛ࣋ͪ߹͢Δ
จ຺ ɹଠׇ͕͍ͨɻ ໌ݐࠃه೦ͩɻ ˠ ݁ଋੑɾҰ؏ੑ͕ͳ͍ ͦͷͨΊɺଠਫΛҿΜͩɻ ˠ ݁ଋੑɾҰ؏ੑ͕͋Δ
൴ਫΛҿΜͩɻ ˠ ݁ଋੑɾҰ؏ੑ͋Δ͕লུ͞Ε͍ͯΔ
ڞࢀর ˗ จষதͷͭͷදݱ͕ಉ͡ࣄΛࢦ͢ ˗ ͭͷදݱͱࢦࣔ͠͞ΕΔࣄͷऀͷؔ ଠׇ͕͍ͨɻ൴ਫΛҿΜͩɻ ࢀর ࢀর
রԠ ˗ ໊ࢺఆ໊ࢺ۟ଞͷදݱ֎քΛࢀর ˗ রԠࢺɿଞΛরԠ͢Δදݱ ˗ ઌߦࢺɿরԠࢺʹࢀর͞ΕΔදݱ ଠׇ͕͍ͨɻ൴ਫΛҿΜͩɻ রԠ
রԠࢺ ઌߦࢺ
લํরԠͱޙํরԠ ˗ લํরԠɿઌߦࢺ͕রԠࢺͷલʹ͋Δ ଠׇ͕͍ͨɻ൴ਫΛҿΜͩɻ ˗ ޙํরԠɿઌߦࢺ͕রԠࢺͷޙʹ͋Δ ࢲ͜Μͳ͕ཉ͍͠ɻͲ͜Ͱߦ͚Δ൶ͩɻ ˗ จ຺রԠɿલํরԠͱޙํরԠͷ૯শ
রԠ রԠࢺ ઌߦࢺ ઌߦࢺ রԠࢺ রԠ
֎քরԠ ˗ ࢀর͞ΕΔࣄ͕ݴޠදݱதʹग़ͳ͍ ൴୭Ͱ͔͢ɻ ͦͷंʹͬͯԼ͍͞ɻ ࢲಡॻ͕͖Ͱ͢ɻ զ͕͓ࣾ٬༷ͷΛେʹ͍ͯ͠·͢ɻ
θϩরԠ ˗ θϩ໊ࢺɿলུ͞ΕͨরԠࢺ ଠׇ͕͍ͨɻ ൴ ਫΛҿΜͩɻ ˗ θϩরԠɿθϩ໊ࢺ͕ଞͷදݱΛࢀর ˗ θϩরԠಛʹຊޠͰݟΒΕΔ
ઌߦࢺ θϩ໊ࢺ θϩরԠ
রԠղੳ ˗ রԠࢺ͕ࢀর͢Δઌߦࢺͷܾఆ ˗ রԠࢺͱઌߦࢺͷڑͳͲΛख͕͔Γʹ͢Δ ൴ˠஉੑɾ୯ ͦΕΛ৯ͨˠ৯ΔͷϮ֨ ͦͷंˠंͷԼҐ֓೦ λΫγʔ ύτΧʔ
θϩরԠղੳ ˗ লུ͞ΕͨরԠࢺΛٻΊΔॲཧ ˗ ໊ࢺఆ໊ࢺ۟ʹΑΔख͕͔Γ͕ͳ͍ ˗ θϩ໊ࢺͷଘࡏΛൃݟ͢Δඞཁ͕͋Δ ˗ ֨ϑϨʔϜͳͲΛར༻ͯ͠ٻΊΔ ˗
/"*45ίʔύεژେίʔύεΛ༻͍ͯ ఔͷਫ਼
ൃදͨ͠༰ ˗ จ຺ ˗ ڞࢀরͱরԠ ˗ લํরԠͱޙํরԠ ˗ จ຺রԠͱ֎քরԠ ˗
θϩরԠ ˗ রԠղੳͱθϩরԠղੳ