Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
文献紹介:参照訳を必要としない単語分散表現による異言語間類似度を用いた訳文の自動評価
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
Taichi Aida
June 12, 2019
Technology
170
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
文献紹介:参照訳を必要としない単語分散表現による異言語間類似度を用いた訳文の自動評価
Taichi Aida
June 12, 2019
Transcript
19 slides
จݙհʢʣ ࢀর༁Λඞཁͱ͠ͳ͍୯ޠࢄදݱʹΑΔ ҟݴޠؒྨࣅΛ༻͍ͨ༁จͷࣗಈධՁ ૬ాɹଠҰ Ԭٕज़Պֶେֶ ࣗવݴޠॲཧݚڀࣨ
LITERATURE ➤ ౻, ӽલ୩, ߥ. ࢀর༁Λඞཁͱ͠ͳ͍୯ޠࢄදݱʹΑΔҟݴޠؒྨࣅΛ༻͍ ͨ༁จͷࣗಈධՁ. ిࢠใ௨৴ֶձ. 2018.
ABSTRACT ➤ ࢀর༁Λ༻͍ͨ༁ͷධՁख๏͕ଘࡏ ➤ Ϣʔβ͕ػց༁Λར༻͢Δࡍࢀর༁Λ༻͍ͳ͍ ➤ QEɿࢀর༁ͷΘΓʹେنͳର༁ίʔύεΛ༻͍Δ ➤ ԤभҎ֎ͷݴޠͰର༁ίʔύε͕͍͠ ➤
ࢀর༁ɺର༁ίʔύεΛ༻͍ͳ͍ධՁํ๏ΛఏҊ
INTRODUCTION ➤ ݱঢ়ͷػց༁ඞͣਖ਼͍͠༁Λग़ྗ͢ΔͱݶΒͳ͍ ➤ খઆͳͲͷந͕ߴ͍จॻͰਖ਼͘͠༁ͤͳ͍ࣄ͕ଟ͍ ➤ ࢀর༁ɺର༁ίʔύεΛ༻͍ͯग़ྗΛධՁ ➤ ࢀর༁ɿ༁จͷ࣭ྔʹґଘ ➤
ର༁ίʔύεɿେنͰ͋Δલఏ ➤ ୯ޠͷҟݴޠؒྨࣅ͔ΒධՁ͢Δख๏ΛఏҊ
PROPOSAL 1. ୯ޠࢄදݱΛֶश 2. ༁ߦྻͰϚοϐϯά 3. ҟݴޠؒྨࣅͷܭࢉ 4. ྨࣅͷग़ྗ
PROPOSALʼ ୯ޠࢄදݱΛֶश ➤ WikipediaͷσʔλͰֶश ➤ ӳޠɿ1.3GB ➤ ຊޠɿ850MB ➤ ࣍ͷurl͔Βμϯϩʔυ
https://dumps.wikimedia.org ➤ ݴޠ͝ͱʹهࣄͷ͕ҟͳΔ ➤ ӳޠ൛ͷํ͕ଟ͔ͬͨ
PROPOSALʼ ༁ߦྻͰϚοϐϯά ➤ ಘΒΕͨࢄදݱΛҟݴޠؒͰൺֱ͍ͨ͠ ➤ Word2VecͰɺҟݴޠؒʹ͓͍ͯ୯ޠؒͷ͕ؔྨࣅ ➤ ϕΫτϧҟͳΔͨΊɺྨࣅܭࢉͰ͖ͳ͍ ➤ ઢܗมɿ༁ߦྻW
➤ ୯ޠϖΞ(xi , zi )Λ࠷খೋ๏Ͱۙࣅ͢Δ
PROPOSALʼ ҟݴޠؒྨࣅͷܭࢉ1 ➤ ΞϥΠϝϯτ ➤ จؒͷྨࣅΛܭࢉ͢Δࡍɺෆཁͳ୯ޠؒͷܭࢉϊΠζ ➤ શͯͷ୯ޠؒͰΞϥΠϝϯτείΞΛܭࢉ ➤ ҎԼͷΑ͏ʹͯ͠୯ޠϕΫτϧؒͷίαΠϯྨࣅ
di Λઃఆ ➤ DICEʢଜΒͷॏΈ͖DICEΛ࠾༻ʣ ➤ ୯ޠؒͷڞىใ f ͔Βܭࢉ tɿᮢʢҙʣ
PROPOSALʼ ҟݴޠؒྨࣅͷܭࢉ2 ➤ EMDɿEarth Mover’s Distance ➤ ྨࣅը૾ݕࡧʹ༻͍ΒΕΔख๏ ➤ ؒͷڑΛ࠷దԽ͢Δࡍɺ༌ૹΛͱʹఆٛ
➤ ֤P , QͦΕͧΕಛྔͱॏΈ͔ΒͳΔγάωνϟͷू߹ ➤ pi ͔Βqj ʹ༌ૹ͢Δ߹ ➤ dij ɿ2ؒͷڑ ➤ fij ɿ༌ૹ͢Δՙྔ ➤ ࣄྔWORKΛ࠷খԽ Ҿ༻ɿ[1]
PROPOSALʼ ҟݴޠؒྨࣅͷܭࢉ3 ➤ EMDɿEarth Mover’s Distance ➤ ҎԼ4ͭͷ੍݅ ➤ ಘΒΕͨ࠷దղ
f*ij Λ༻͍ͯɺ P , QؒͷڑΛܭࢉ Ҿ༻ɿ[1]
PROPOSALʼ ྨࣅͷग़ྗ ➤ ࠓճͷ݅ʹ͓͍ͯɺdijɿҟݴޠؒͷ୯ޠͷྨࣅ ➤ ಘΒΕͨEMDΑΓɺจؒͷྨࣅҎԼͷΑ͏ʹදͤΔ
EXPERIMENT ➤ σʔλ ➤ ʮThe Old Capitalʯ ➤ ݪจɿ߁ʮݹʯ ➤
಄100จΛ༻ ➤ ༁ʢӳˠʣ ➤ Google༁ ➤ Microsoft Translator ➤ Excite༁ ➤ ༁จͷධՁʢਓखʣ ➤ 8ਓͷཧܥେֶӃੜ ➤ 5ஈ֊ͰධՁ ➤ શһͷฏۉΛ༁จͷͱͨ͠
EXPERIMENT ➤ σʔλ ➤ ʮThe Old Capitalʯ ➤ ݪจɿ߁ʮݹʯ ➤
಄100จΛ༻ ➤ ༁ʢӳˠʣ ➤ Google༁ ➤ Microsoft Translator ➤ Excite༁ ➤ ༁จͷධՁʢਓखʣ ➤ 8ਓͷཧܥେֶӃੜ ➤ 5ஈ֊ͰධՁ ➤ શһͷฏۉΛ༁จͷͱͨ͠ ਓखධՁͷॱҐ༁ 1→༁ 2→༁ 3
EXPERIMENT ➤ ධՁํ๏ ɹ3ͭͷ༁จʹରͯ͠ɺྨࣅॱʹॱҐΛ࡞ ×100จ ➤ ਖ਼ղʢਓखͱͷશҰகʣ ➤ έϯυʔϧͷॱҐ૬ؔ ➤
༁จͷॱҐͷେখؔͷ૬ؔ ➤ ൺֱର ➤ ఏҊख๏ ➤ ॏΈʴΞϥΠϝϯτ ➤ ॏΈͳ͠ ➤ ΞϥΠϝϯτͳ͠ ➤ ࣗಈධՁई ➤ METEOR ➤ RIBES
RESULT ➤ ఏҊख๏METEORΛ্ճΓɺRIBES ʹഭΔ݁Ռ ➤ ୯ޠͷΞϥΠϝϯτ͕େ͖͘࡞༻͍ͯͨ͠
DISCUSSION ➤ ఏҊख๏ͷᮢʹର͢ΔҰகɺॱҐ૬ؔ ➤ ᮢΛ্͛Δ΄ͲҰக্͕Δ ➤ ᮢ0.73, 1.46ͰϐʔΫΛܴ͑Δ͕ɺޙऀҰக͕গͳ͍ ➤ ᮢ͕ߴ͘ͳΔ΄Ͳܭࢉʹඞཁͳ୯ޠϖΞഉআ͞ΕΔ
DISCUSSION ➤ RIBESਓखͱࣅͨॱͰධՁ͍ͯ͠Δ͕ɺఏҊख๏ҟͳΔ ➤ ఏҊख๏༁ௐͷ༁จΛߴ͘ධՁ͕ͪ͠
CONCLUSION ➤ ࢀর༁ର༁ίʔύε༻͍ͳ͍ධՁख๏ΛఏҊ ➤ ҟݴޠؒͷࢄදݱΛઢܗม͢Δ༁ߦྻ ➤ ྨࣅը૾ݕࡧʹ༻͍ΒΕΔEMDͰจؒྨࣅΛࢉग़ ➤ METEORΛ্ճΓɺRIBESʹഭΔ݁Ռͱͳͬͨ ➤
ఏҊख๏ͷੑೳʹ୯ޠͷΞϥΠϝϯτ͕ޮ͍͍ͯͨ ➤ ࢺใΛߟྀ͠ɺ୯ޠͷΞϥΠϝϯτΛվળ͍ͨ͠
REFERENCES 1. aidiary. Earth Mover’s Distance(EMD). ਓೳʹؔ͢Δஅ. 2012. http://aidiary.hatenablog.com/entry/20120804/1344058475
More Decks by Taichi Aida
See All by Taichi Aida
意味を表すベクトル表現を用いたテキスト分析
a1da4
0
180
スウェーデン滞在報告
a1da4
0
56
PhD Defence: Considering Temporal and Contextual Information for Lexical Semantic Change Detection
a1da4
1
350
文献紹介:A Multidimensional Framework for Evaluating Lexical Semantic Change with Social Science Applications
a1da4
1
450
YANS2024:目指せ国際会議!「ネットワーキングの極意(国際会議編)」
a1da4
0
370
言語処理学会30周年記念事業留学支援交流会@YANS2024:「学生のための短期留学」
a1da4
1
500
新入生向けチュートリアル:文献のサーベイv2
a1da4
19
14k
文献紹介:Isotropic Representation Can Improve Zero-Shot Cross-Lingual Transfer on Multilingual Language Models
a1da4
0
280
文献紹介:WhitenedCSE: Whitening-based Contrastive Learning of Sentence Embeddings
a1da4
1
430
Other Decks in Technology
See All in Technology
Biohub - Cell Tracking During Development 5th place solution
rist
0
150
内製アプリとClaudeスキルのセキュリティチェック、 Backlogの課題で回しています。
ayaka_egaaa
0
180
DBTS2026 盛り上がってますか!?Databricksが実現するAI時代のデータ基盤
akuwano
1
200
GCASアップデート(202607-202610)
techniczna
1
330
20261113_JAWS_Osaka
takuyay0ne
0
390
JAWSコミュニティに 参加して1年経った結果
ssakita
0
140
狙われているAPIの脆弱性!今こそ手をつけるべき根本的な対策とは?
nagix
0
130
人間+AIを「チーム」としてプロセスを再設計する
littlehands
1
1.6k
これからのデータエンジニアの役割について考える / Rethinking the Role of Data Engineers in the AI Era
okiyuki99
0
480
複数システムが同居した 15 年物の AWS アカウントを解体するための考古学
wa6sn
3
150
速くなった開発の効果をどう推し量るのか
bulbulpaul
0
110
ライフワーク「猫でもわかるDirectConnect」
kentapapa
0
330
Featured
See All Featured
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
360
31k
Reflections from 52 weeks, 52 projects
jeffersonlam
356
22k
How GitHub (no longer) Works
holman
316
150k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
9
1.7k
Chasing Engaging Ingredients in Design
codingconduct
0
390
We Are The Robots
honzajavorek
0
440
How to Align SEO within the Product Triangle To Get Buy-In & Support - #RIMC
aleyda
2
1.9k
[RailsConf 2023] Rails as a piece of cake
palkan
59
7.1k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
25
2.2k
The State of eCommerce SEO: How to Win in Today's Products SERPs - #SEOweek
aleyda
2
12k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
38
3.1k
Agile Actions for Facilitating Distributed Teams - ADO2019
mkilby
0
340