$30 off During Our Annual Pro Sale. View Details »
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
0
200
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
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
200
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
250
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
170
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
170
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
290
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
360
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 Technology
See All in Technology
IaC を使いたくないけどポリシー管理をどうにかしたい
kazzpapa3
1
210
インフラ室事例集
mixi_engineers
PRO
2
170
ページの可視領域を算出する方法について整理する
yamatai1212
0
140
AIにおける自由の追求
shujisado
2
430
Dify on AWS の選択肢
ysekiy
0
120
小規模チームによる衛星管制システムの開発とスケーラビリティの実現
sankichi92
0
180
Symfony AI in Action
el_stoffel
2
300
生成AIシステムとAIエージェントに関する性能や安全性の評価
shibuiwilliam
2
300
セキュリティAIエージェントの現在と未来 / PSS #2 Takumi Session
flatt_security
2
800
オープンデータの内製化から分かったGISデータを巡る行政の課題
naokim84
2
1.3k
AI/MLのマルチテナント基盤を支えるコンテナ技術
pfn
PRO
4
600
Contract One Engineering Unit 紹介資料
sansan33
PRO
0
9.8k
Featured
See All Featured
The Illustrated Children's Guide to Kubernetes
chrisshort
51
51k
The Power of CSS Pseudo Elements
geoffreycrofte
80
6.1k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
3.2k
YesSQL, Process and Tooling at Scale
rocio
174
15k
[RailsConf 2023] Rails as a piece of cake
palkan
58
6.1k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
48
9.8k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
231
22k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
34
2.5k
Leading Effective Engineering Teams in the AI Era
addyosmani
8
1.2k
Designing for Performance
lara
610
69k
Music & Morning Musume
bryan
46
7k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
249
1.3M
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