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
0
140
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
Tweet
Share
More Decks by Taichi Aida
See All by Taichi Aida
PhD Defence: Considering Temporal and Contextual Information for Lexical Semantic Change Detection
a1da4
0
120
文献紹介:A Multidimensional Framework for Evaluating Lexical Semantic Change with Social Science Applications
a1da4
1
250
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
150
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
300
新入生向けチュートリアル:文献のサーベイv2
a1da4
13
9.4k
文献紹介:Isotropic Representation Can Improve Zero-Shot Cross-Lingual Transfer on Multilingual Language Models
a1da4
0
150
文献紹介:WhitenedCSE: Whitening-based Contrastive Learning of Sentence Embeddings
a1da4
1
210
文献紹介:On the Transformation of Latent Space in Fine-Tuned NLP Models
a1da4
0
78
新入生向けチュートリアル:文献のサーベイ
a1da4
0
430
Other Decks in Technology
See All in Technology
Reading Code Is Harder Than Writing It
trishagee
2
120
Potential EM 制度を始めた理由、そして2年後にやめた理由 - EMConf JP 2025
hoyo
2
1.5k
白金鉱業Meetup Vol.17_あるデータサイエンティストのデータマネジメントとの向き合い方
brainpadpr
7
980
Two Blades, One Journey: Engineering While Managing
ohbarye
3
680
わたしがEMとして入社した「最初の100日」の過ごし方 / EMConfJp2025
daiksy
12
3.4k
Active Directory攻防
cryptopeg
PRO
8
4.9k
生成 AI プロダクトを育てる技術 〜データ品質向上による継続的な価値創出の実践〜
icoxfog417
PRO
5
1.9k
依存パッケージの更新はコツコツが勝つコツ! / phpcon_nagoya2025
blue_goheimochi
3
190
PHPで印刷所に入稿できる名札データを作る / Generating Print-Ready Name Tag Data with PHP
tomzoh
0
180
設計を積み重ねてシステムを刷新する
sansantech
PRO
0
130
ディスプレイ広告(Yahoo!広告・LINE広告)におけるバックエンド開発
lycorptech_jp
PRO
0
190
Share my, our lessons from the road to re:Invent
naospon
0
120
Featured
See All Featured
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
356
29k
Fashionably flexible responsive web design (full day workshop)
malarkey
406
66k
A better future with KSS
kneath
238
17k
The Invisible Side of Design
smashingmag
299
50k
Building Adaptive Systems
keathley
40
2.4k
Fantastic passwords and where to find them - at NoRuKo
philnash
51
3k
Testing 201, or: Great Expectations
jmmastey
42
7.2k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
666
120k
Building a Scalable Design System with Sketch
lauravandoore
461
33k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
366
25k
Site-Speed That Sticks
csswizardry
4
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