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: 単語アライメントを用いた英日機械翻訳文の流暢さの自動評価
Search
Yumeto Inaoka
May 19, 2017
Technology
200
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
文献紹介: 単語アライメントを用いた英日機械翻訳文の流暢さの自動評価
2017/05/19の文献紹介で発表
Yumeto Inaoka
May 19, 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
220
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
280
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
210
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
210
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
430
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
280
Other Decks in Technology
See All in Technology
最近評価が難しくなった
maroon8021
0
330
AIと共生する開発者プラットフォーム:バクラクのモノレポ×マイクロサービス基盤
sakajunquality
2
3.4k
ruby.wasmとPicoRuby.wasmに対応した仮想DOMライブラリを作ってる話 #kaigieffect_kaigi
sue445
PRO
0
140
なぜ私たちのSREプラクティスはなかなか機能しないのか 〜システムより先に組織を見る〜 / Why our SRE practices aren't really working
vtryo
3
3.6k
Zoom2Youtube.Claude
kawaguti
PRO
3
490
貴方はどのエンジニアリングを磨くのか
hatyibei
0
120
ソニー銀行におけるビジネスアジリティ向上のためのクラウドシフト戦略
srenext
0
140
Genie Ontologyは銀の弾丸かを考える / Is Genie Ontology a Silver Bullet?
nttcom
0
240
ヘルスケア領域における AI 活用と その安全性担保のための取り組み (Leveraging AI in Healthcare and Our Efforts to Ensure Its Safety) - Google I/O Extended Tokyo 2026, July 11, 2026
zettaittenani
0
270
【Claude Code】鹿野さんに聞く 私の推しの並行開発環境 大公開 / claude-code-parallel-2026-07-15
tonkotsuboy_com
10
6.6k
cccccc
moznion
0
1.9k
ループエンジニアリングでE2Eテストを実践
noriyukitakei
0
350
Featured
See All Featured
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
287
14k
Lessons Learnt from Crawling 1000+ Websites
charlesmeaden
PRO
1
1.4k
Navigating Weather and Climate Data
rabernat
0
310
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
62
44k
RailsConf 2023
tenderlove
30
1.5k
Marketing Yourself as an Engineer | Alaka | Gurzu
gurzu
0
260
Digital Ethics as a Driver of Design Innovation
axbom
PRO
1
340
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
141
35k
A brief & incomplete history of UX Design for the World Wide Web: 1989–2019
jct
2
420
The Illustrated Children's Guide to Kubernetes
chrisshort
51
52k
Being A Developer After 40
akosma
91
590k
AI: The stuff that nobody shows you
jnunemaker
PRO
8
820
Transcript
୯ޠΞϥΠϝϯτΛ༻͍ͨ ӳػց༁จͷྲྀெ͞ͷࣗಈධՁ จݙհ ࣗવݴޠॲཧݚڀࣨɹҴԬເਓ ٢ݟؽ খ୩ࠀଇ ݟؽ ࠤా͍ͪࢠ
Ҫࠤݪۉ ࣗવݴޠॲཧ 7PM /P QQ
֓ཁ ˗ ػց༁γεςϜ ࣙॻ نଇ ͷྲྀெ͞ΛࣗಈධՁ ૉੑͱͯ͠୯ޠΞϥΠϝϯτΛ༻ ࣗಈධՁ࣌ʹࢀর༁͕ෆཁ
˗ γεςϜ༁ͷಛੳ γεςϜ༁ʹಛతͳૉੑΛ؍ ػց༁γεςϜͷ࣭Λվળ
ػց༁γεςϜͷධՁ ˗ ద͞ ݪจʹΑͬͯಡऀʹΘΔใͷ͏ͪ Ͳͷఔ͕༁จʹΑͬͯΘΔ͔ ˗ ྲྀெ͞ ༁จ͕తݴޠͷจͱͯ͠Ͳͷఔྲྀெ͔ ݪจͱಠཱʹଌΔ
ྲྀெ͞ԼͷཁҼ ˗ ෆࣗવͳஞޠ༁ ஞޠ༁Λ͖͢Ͱͳ͍߹ʹ͓͚Δஞޠ༁ γεςϜ༁ʹଟ͘ൃੜ ˗ ஞޠ༁ͷҧ͍ʹΑΔγεςϜ༁ͷྲྀெ͞ΛධՁ
ෆࣗવͳஞޠ༁ ˗ &ݪจɹ)ਓؒ༁ɹ.YγεςϜ༁ ˗ NBLFͷஞޠ༁͕ҟͳΔ
ෆࣗવͳஞޠ༁ ˗ IF JUͷஞޠ༁͕ҟͳΔ
࣮ݧ ˗ ϩΠλʔӳର༁ίʔύε ˗ Ұ෦ΛਓखධՁʢྲྀெ͞ɺద͞ʣ ˗ ࢢൢͷػց༁γεςϜͭΛ༻ ˗ αϙʔτϕΫλϚγϯʹΑΔਓख༁ͱ ػց༁ͷࣝผ
ਓखධՁͷ݁Ռ ˗ ྲྀெ্͕͞ॏཁͳ՝ͱݴ͑Δ
୯ޠରͷग़ݱස ˗ γεςϜ༁୯ޠରԠ͕͖͍͢
ࣝผਖ਼ղ ˗ ఏҊख๏ͰγεςϜ༁͔൱͔Λࣝผ ˗ ະରԠ୯ޠͷํ͕ࣝผʹ༗ޮ
ࣄྫͷࣝผਖ਼ղͷӨڹ ˗ ఔͷਓؒ༁ʹ͓͍ͯҎ্
˗ ະରԠ୯ޠΛ༻͍ͨ߹ɺྲྀெ͞ʹΑΔ ਖ਼ղͷมԽͳ͠ ྲྀெ͞ͱࣝผਖ਼ղͷؔ
ྲྀெ͞ͱࣝผਖ਼ղͷؔ ˗ ྲྀெ͕͞ߴ͍΄Ͳࣝผਖ਼ղԼ ˠࣝผਖ਼ղΛྲྀெ͞ͷईͱͯ͠ར༻Ͱ͖Δ ɹ͜ͱΛࣔࠦ
ࣝผʹ͓͚ΔॏΈ
γεςϜ༁ͷಛੳ ˗ ಄ࣙʮಉʯ͕ਓؒ༁ʹؚ·ΕΔ ˗ ӳޠͰͷ໊ࢺΛຊޠͰଞͷදݱͱͯ͠ ༁Ͱ͖ΔΑ͏ʹ͢Δ͜ͱ͕ॏཁ
·ͱΊ ˗ γεςϜ༁ͷྲྀெ͞ΛࣗಈධՁ͢Δख๏ΛఏҊ ˗ ୯ޠΞϥΠϝϯτͰྲྀெ͞ͷҧ͍Λัଊ ˗ ఏҊख๏ʹΑΓࣗಈධՁΛࢧԉͰ͖Δ͜ͱΛࣔࠦ ˗ จϨϕϧͰͷಛੳ͕Մೳ