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: 日本語学習者の作文における 誤用タイプの階層的アノテーションに基づく機械学習による...
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
Yumeto Inaoka
February 23, 2017
Technology
280
0
Share
文献紹介: 日本語学習者の作文における 誤用タイプの階層的アノテーションに基づく機械学習による自動分類
2017/02/23の文献紹介で発表
Yumeto Inaoka
February 23, 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
要件定義の精度を高めるための型と生成AIの活用 / Using Types and Generative AI to Improve the Accuracy of Requirements Definition
haru860
0
310
Vision Banana: Image Generators are Generalist Vision Learners
kzykmyzw
0
310
生成AIはソフトウェア開発の革命か、ソフトウェア工学の宿題再提出なのか -ソフトウェア品質特性の追加提案-
kyonmm
PRO
2
860
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
Google Cloud Next '26 の裏でこっそりリリースされたCloud Number Registry & Cloud Hub コスト分析 を試してみた
hikaru1001
0
170
ハーネスエンジニアリング入門
knishioka
0
130
GitHub Copilot CLI と VS Code Agent Mode の使い分け
tomokusaba
0
140
エージェント時代の UIとAPI、CLI戦略
coincheck_recruit
0
150
AI時代に、 データアナリストがデータエンジニアに異動して
jackojacko_
0
210
ボトムアップの改善の火を灯し続けろ!〜支援現場で学んだ、消えないための3つの打ち手〜 / 20260509 Kazuki Mori
shift_evolve
PRO
2
590
試作とデモンストレーション / Prototyping and Demonstrations
ks91
PRO
0
190
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
Featured
See All Featured
Leading Effective Engineering Teams in the AI Era
addyosmani
9
1.9k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
666
130k
Designing for humans not robots
tammielis
254
26k
How GitHub (no longer) Works
holman
316
150k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
How to Get Subject Matter Experts Bought In and Actively Contributing to SEO & PR Initiatives.
livdayseo
0
110
Data-driven link building: lessons from a $708K investment (BrightonSEO talk)
szymonslowik
1
1k
AI Search: Where Are We & What Can We Do About It?
aleyda
0
7.4k
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
200
SEOcharity - Dark patterns in SEO and UX: How to avoid them and build a more ethical web
sarafernandez
0
180
Imperfection Machines: The Place of Print at Facebook
scottboms
270
14k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
32
2.9k
Transcript
ຊޠֶशऀͷ࡞จʹ͓͚Δ ޡ༻λΠϓͷ֊తΞϊςʔγϣϯ ʹجͮ͘ػցֶशʹΑΔࣗಈྨ จݙհ ࣗવݴޠॲཧݚڀࣨɹҴԬເਓ େࢁߒඒ খொक দຊ༟࣏
ݴޠॲཧֶձ 7PM /P QQ
֓ཁ ˗ /"*45ޡ༻ίʔύεͷ࡞ ˗ ্هίʔύεʹΑΔޡ༻λΠϓͷࣗಈྨ ˠ࣮༻ʹת͑͏Δద߹ ׂఔ ͷ࣮ݱ ˗ ޡ༻λΠϓʹ֊ߏΛར༻ͨ͠ྨ
ˠྨਫ਼͕ϙΠϯτ্ ˗ ฤूڑͱஔ֬Λ৽ͨʹૉੑͱͯ͠ར༻ ˠྨਫ਼͕ϙΠϯτ্
എܠ ˗ ݴޠֶशऀίʔύεͷௐࠪݚڀͷར༻ ˗ ֶशऀͷ࡞จΛޡ༻λΠϓผʹͯ͠׆༻͍ͨ͠ ˗ େنͳίʔύεΛਓखͰྨ͢Δͷࠔ 㱺ػցֶशΛ༻͍ͨޡ༻จͷޡ༻λΠϓผͷྨ
/"*45ޡ༻ίʔύεͷ࡞ ˗ ࠃཱࠃޠݚڀॴͷ࡞จର༁%#ͷλά͚ ˗ ఴΛมߋͤͣʹޡ༻λάΛΞϊςʔγϣϯ ˗ શޡ༻λΠϓछΛ֊తʹఆٛ ˗ ୈ֊छɺ͏ͪछΛબ
ޡ༻λάͷΞϊςʔγϣϯ TͦΕͰɼHPZPUZQFlTFNzUZQFlOPULKz DSSlৗʹz·͍ʹͪHPZP͕͍͘͜ͷ͑Μ͡ΐ͕ ͍Γ·͢ɽT ˗ ޡ༻ՕॴʹHPZPλάΛઃ͚Δ ˗ ਖ਼༻ՕॴΛDSSଐੑͰࢦఆ ˗ ޡ༻λΠϓΛUZQFଐੑͰࢦఆ
ޡ༻λΠϓͷྨ ˗ ୈஈ֊Ͱʮෆʯʮ༨ʯ ʮஔʯʹྨ ˗ ʮஔʯͰʮจ๏తޡ༻ʯ ʮޠኮతޡ༻ʯʹྨ ˗ ʮ\จ๏ ޠኮ^తޡ༻ʯͷ
ͦΕͧΕͰྨ
࣮ݧํ๏ ˗ /"*45ޡ༻ίʔύε͔Βͷ ࣄྫʹΑΔ ׂަࠩݕఆ ˗ จʹผʑͷޡ༻͕ݸҎ্͋Δ߹ ޡ༻ʹ͖ͭࣄྫ ˗ ޡ༻λΠϓΛ֊ߏԽͨ͠߹ͱ
͠ͳ͔ͬͨ߹ͷ྆ํͰ࣮ݧ
࣮ݧͷྲྀΕ ˗ ޡ༻ՕॴY ਖ਼༻ՕॴZ ޡ༻λΠϓUͷͭͷ ϥϕϧ Y Z U ΛऔΓग़͢
˗ ࣄྫ͝ͱʹૉੑΛ༩ ˗ ࠷େΤϯτϩϐʔ๏Λ༻͍ͯଟΫϥεྨ
ૉੑ
ฤूڑ ˗ ͭͷจࣈྻͷҧ͍Λࣔ͢ڑ ˗ จࣈͷૠೖɾআɾஔΛ࠷খͰԿճߦ͑ Ұํ͔Β͏ҰํͷจࣈྻʹͳΔ͔ ˗ ྫ LJUUFOͱTJUUJOH LJUUFOˠTJUUFOˠTJUUJOˠTJUUJOH
ճͷखॱͰग़དྷΔͷͰฤूڑ
ஔ֬ ˗ ޡ༻ஔ֬ ޡ༻ͲͷΑ͏ʹగਖ਼͞Ε͍ͯΔ͔ ˗ ਖ਼༻ஔ֬ ਖ਼༻จͲͷΑ͏ͳޡ༻͔Βగਖ਼͞Ε͍ͯΔ͔
ධՁई
࣮ݧ݁Ռ ֊ߏ
࣮ݧ݁Ռ ֊ߏ ϙΠϯτ
࣮ݧ݁Ռ ֊ߏ
࣮ݧ݁Ռ ֊ߏ
࣮ݧ݁Ռ ֊ߏ ࣄྫ ࣄྫ ࣄྫ
࣮ݧ݁Ռ ฤूڑɾஔ֬
࣮ݧ݁Ռ ฤूڑɾஔ֬ ϙΠϯτ
࣮ݧ݁Ռ ฤूڑɾஔ֬ ϙΠϯτ
࣮ݧ݁Ռ ฤूڑɾஔ֬ ϙΠϯτ
࣮ݧ݁Ռ ֊ຖ
ฤूڑૉੑʹΑΔੑೳ্ ˗ ޠኮબɿࣈˠࣈɹඇࣈˠࣈ ˗ දهɿฏԾ໊ˠࣈ ˗ ༨ɿจࣈྻ͕͍ͷˠ㱵
ஔ֬ʹΑΔੑೳ্ ˗ ಈࢺɿϕʔεϥΠϯ ฤूڑͰ ɹɹɹจମʹྨ͞ΕΔͷ ˗ ෆɿϕʔεϥΠϯ ฤूڑͰ ɹɹɹॿࢺʹྨ͞ΕΔͷ
จ຺ͱੑೳͷؔ ˗ จ຺ͷ֦େੑೳ্ʹͭͳ͕Βͳ͍ ˗ จ຺ใޡ༻λΠϓྨʹෆཁͳՄೳੑ ˗ ޡ༻෦ͷपลܗଶૉղੳ͕ࣦഊ͍͢͠ ˗ ݴޠֶशऀͷ࡞จܗଶૉղੳ͕ࠔ
·ͱΊ ˗ ຊޠֶशऀͷޡ༻λά͖ίʔύε ʮ/"*45ޡ༻ίʔύεʯͷ࡞Λߦͬͨ ˗ ޡ༻λΠϓྨΛ֊ߏʹͯ͠ྨੑೳͷ ্Λਤͬͨ ˗ ֦ுૉੑͱͯ͠ฤूڑͱஔ֬ΛՃ͠ ྨੑೳΛ্ͤͨ͞
˗ ॳͷޡ༻λΠϓࣗಈྨثʹ͓͍࣮ͯ༻తͳ ਫ਼Λୡͨ͠