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: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
Taichi Aida
June 12, 2019
Technology
150
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
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
140
スウェーデン滞在報告
a1da4
0
31
PhD Defence: Considering Temporal and Contextual Information for Lexical Semantic Change Detection
a1da4
1
300
文献紹介:A Multidimensional Framework for Evaluating Lexical Semantic Change with Social Science Applications
a1da4
1
400
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
330
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
450
新入生向けチュートリアル:文献のサーベイv2
a1da4
18
12k
文献紹介:Isotropic Representation Can Improve Zero-Shot Cross-Lingual Transfer on Multilingual Language Models
a1da4
0
240
文献紹介:WhitenedCSE: Whitening-based Contrastive Learning of Sentence Embeddings
a1da4
1
390
Other Decks in Technology
See All in Technology
GoとSIMDとWasmの今。
askua
3
520
AIプラットフォームを運用し続けるための可観測性
tanimuyk
4
1.2k
ブロックチェーン / Blockchain
ks91
PRO
0
110
新規ゲーム開発におけるAI駆動開発のリアル
202409e2
0
3k
Building applications in the Gemini API family.
line_developers_tw
PRO
0
2.3k
あなたの AI ワークスペースに、 専門コーダーを連れてくる - Amazon Quick Desktop 最新情報
kawaji_scratch
1
110
AI Testing Talks: Challenges of Applying AI in Software Testing: From Hype to Practical Use
exactpro
PRO
1
140
Claude Code×Terraform IaC テンプレート駆動開発
itouhi
1
450
NAB Show 2026 動画技術関連レポート / NAB Show 2026 Report
cyberagentdevelopers
PRO
0
120
AI-DLCを活用した高品質・安全なAI駆動開発実践 / AI Driven Development with AI-DLC
yoshidashingo
0
150
「コーディング」しない人のための Claude Code 入門 ChatGPT の次の一歩 — 業務に組み込む 育成・共有・自動化
rfdnxbro
2
1.2k
AmazonRoute 53ではじめてのドメイン取得!HTTPS化までの道のりを整理してみた
usanchuu
3
100
Featured
See All Featured
Facilitating Awesome Meetings
lara
57
6.9k
GitHub's CSS Performance
jonrohan
1033
470k
Designing for Timeless Needs
cassininazir
1
250
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
35
2.5k
[RailsConf 2023] Rails as a piece of cake
palkan
59
6.7k
Code Reviewing Like a Champion
maltzj
528
40k
The #1 spot is gone: here's how to win anyway
tamaranovitovic
2
1.1k
Ethics towards AI in product and experience design
skipperchong
2
300
16th Malabo Montpellier Forum Presentation
akademiya2063
PRO
0
140
Color Theory Basics | Prateek | Gurzu
gurzu
0
360
What’s in a name? Adding method to the madness
productmarketing
PRO
24
4.1k
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
400
Transcript
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