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
注意機構を用いた言語創発ゲーム
Search
Ryokan RI
August 19, 2023
Research
0
210
注意機構を用いた言語創発ゲーム
2023 JSAI オーガナイズドセッション
言語とコミュニケーションの創発 ~記号創発システムから共創的言語進化まで~
Ryokan RI
August 19, 2023
Tweet
Share
More Decks by Ryokan RI
See All by Ryokan RI
Language is primarily a tool for communication rather than thought
ryou0634
4
1k
マルチリンガルな言語モデル入門:これまでとこれから
ryou0634
4
4.4k
What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary
ryou0634
0
680
人工言語を使った事前訓練:言語間転移が可能なエンコーダの持っている知識とは何か?
ryou0634
0
920
MIROSTAT で意外さを コントロールした文章生成
ryou0634
1
940
Other Decks in Research
See All in Research
MIRU2025 チュートリアル講演「ロボット基盤モデルの最前線」
haraduka
14
7.1k
在庫管理のための機械学習と最適化の融合
mickey_kubo
3
1.1k
Adaptive fusion of multi-modal remote sensing data for optimal sub-field crop yield prediction
satai
3
250
カスタマーサクセスの視点からAWS Summitの展示を考える~製品開発で活用できる勘所~
masakiokuda
2
180
利用シーンを意識した推薦システム〜SpotifyとAmazonの事例から〜
kuri8ive
1
240
「どう育てるか」より「どう働きたいか」〜スクラムマスターの最初の一歩〜
hirakawa51
0
820
Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
satai
3
160
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
shunk031
14
9.7k
20250725-bet-ai-day
cipepser
2
380
数理最適化と機械学習の融合
mickey_kubo
16
9.2k
日本語新聞記事を用いた大規模言語モデルの暗記定量化 / LLMC2025
upura
0
130
生成的推薦の人気バイアスの分析:暗記の観点から / JSAI2025
upura
0
250
Featured
See All Featured
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
139
34k
KATA
mclloyd
32
14k
Fantastic passwords and where to find them - at NoRuKo
philnash
51
3.4k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
36
2.5k
How to train your dragon (web standard)
notwaldorf
96
6.2k
Visualization
eitanlees
146
16k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
50k
The Cost Of JavaScript in 2023
addyosmani
53
8.8k
The Straight Up "How To Draw Better" Workshop
denniskardys
236
140k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
32
1.4k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
30
9.6k
Transcript
ҙػߏΛ༻͍ͨ ݴޠൃήʔϜ ཥ ྇פɹ্ా ྄ɹJason Naradowsky ౦ژେֶ
ࢦࣔήʔϜͱʁ - ίϛϡχέʔγϣϯ͔Βࢦࣔͷଆ໘͚ͩΛऔΓग़ͨ͠ήʔϜɻ - ൃίϛϡχέʔγϣϯͷݚڀͰΑ͘ΘΕΔɻ ࢦࣔήʔϜ (referential game)
ࢦࣔήʔϜ (referential game) Speaker 3 14 2 25 ඪΦϒδΣΫτ Listener
ΦϒδΣΫτީิू߹
ࢦࣔήʔϜ (referential game) Speaker 3 14 2 25 Listener ඪΦϒδΣΫτ
ΦϒδΣΫτީิू߹ ᶃ Speaker ͕ ඪΦϒδΣΫτΛݟͯ ϝοηʔδΛੜ
ࢦࣔήʔϜ (referential game) Speaker 3 14 2 25 Listener ඪΦϒδΣΫτ
ΦϒδΣΫτީิू߹ ᶄ Listener ͕ϝοηʔδΛݟͯ ΦϒδΣΫτީิू߹͔Β ඪΦϒδΣΫτΛ༧ଌ͢Δ
ࢦࣔήʔϜ (referential game) Speaker 3 14 2 25 ඪΦϒδΣΫτ Listener
ΦϒδΣΫτީิू߹ ᶅ Listener ͷ༧ଌͱ ඪΦϒδΣΫτ͕Ұக͍ͯ͠Ε ใु͕༩͑ΒΕΔɻ
ࢦࣔήʔϜͷΤʔδΣϯτʹҙػߏΛ࣮͢Δ ຊݚڀͰͬͨ͜ͱ Speaker Listener
ͳͥҙػߏ͔ʁ - ൃݴޠͷߏੑ্͕͕Δͣ - ൃݴޠͷղऍੑ্͕͕Δͣ ຊݚڀͰͬͨ͜ͱ
ͳͥҙػߏ͔ʁ - ൃݴޠͷߏੑ্͕͕Δͣ - ൃݴޠͷղऍੑ্͕͕Δͣ ຊݚڀͰͬͨ͜ͱ
ߏੑͱɿશମ͕෦ͷ૯͔ΒͳΔ͜ͱ ҙػߏൃݴޠͷߏੑΛ্͛Δʁ ߏੑ ߴ🔺 ߏੑ 🔻 5 3 2 3
2 1 6 4
ҙػߏൃݴޠͷߏੑΛ্͛Δʁ 5 Speaker ҙػߏ୯ޠͱΦϒδΣΫτͷ෦ͷ݁ͼ͖ͭ Λֶश͢Δͷʹཱͪͦ͏
ͳͥҙػߏ͔ʁ - ൃݴޠͷߏੑ্͕͕Δͣ - ൃݴޠͷղऍੑ্͕͕Δͣ ຊݚڀͰͬͨ͜ͱ
ҙػߏൃݴޠͷղऍੑΛ্͛Δʁ 5 Speaker ͜ͷ୯ޠ͜ͷҙຯͳͷͩͱΘ͔Δ
࣮ݧઃఆɿࢦࣔήʔϜ Speaker 3 14 2 25 ඪΦϒδΣΫτ Listener ΦϒδΣΫτީิू߹ Fashion
MNIST Λ༻͍ͨࢦࣔήʔϜ ʢεχʔΧʔͱϓϧΦʔόʔʣ
࣮ݧઃఆɿࢦࣔήʔϜ Speaker 3 14 2 25 ඪΦϒδΣΫτ Listener ΦϒδΣΫτީิू߹ Fashion
MNIST Λ༻͍ͨࢦࣔήʔϜ ʢεχʔΧʔͱϓϧΦʔόʔʣ
FashionMNIST - 10 छྨͷΞΠςϜͷը૾ΛؚΉσʔληοτ ࣮ݧઃఆɿࢦࣔήʔϜ
FashionMNIST - 10 छྨͷΞΠςϜͷը૾ΛؚΉσʔληοτ ࣮ݧઃఆɿࢦࣔήʔϜ ̎छྨͷΞΠςϜΛબΜͰ ̍ͭͷΦϒδΣΫτΛ࡞Δ
࣮ݧઃఆɿࢦࣔήʔϜ FashionMNIST Λ༻͍ͨࢦࣔήʔϜ - FashionMNIST த͔Βը૾Λαϯϓϧͯ͠ଟ༷ͳΦϒδΣΫ τΛ࡞ɻ - ಉ͡छྨͷΞΠςϜؚ͕·Ε͍ͯΕಉ͡ΦϒδΣΫτͰ͋Δ ͱΈͳ͢ɻ
- ΦϒδΣΫτͷछྨ - ܇࿅ηοτʹ30छྨɺධՁηοτʹ15छྨ༻ 10 C2 = 45
࣮ݧઃఆɿࢦࣔήʔϜ ਓؒʹ͍ۙݴޠΛֶश͢ΔͨΊʹ ಉ͡छྨͷҟͳΔΦϒδΣΫτΛ Speaker ͱ Listener ʹݟͤΔ ඪΦϒδΣΫτ ΦϒδΣΫτީิू߹
ҙػߏͳ͠ͷ Speaker ҙػߏ͋Γͷ Speaker ࣮ݧઃఆɿϞσϧ ҙػߏͳ͠ͷ Listner ҙػߏ͋Γͷ Listener ×
ͦΕͧΕͷΈ߹ΘͤͰ࣮ݧ ͞ΒʹΤʔδΣϯτΛ࣮͢ΔωοτϫʔΫͱͯ͠ LSTM ͱ Transformer ͦΕͧΕͰ࣮ݧ
࣮ݧઃఆɿϞσϧ ϕʔεϥΠϯɾΤʔδΣϯτ otgt o1 %FDPEFS &ODPEFS m1 m2 m3 ϝοηʔδΦϒδΣΫτ
߹கείΞ m0 m1 m2 m1 m2 m3 Speaker Listener - ҙػߏͳ͠ - ΦϒδΣΫτ୯ҰͷϕΫτϧͰදݱ͞ΕΔ
࣮ݧઃఆɿϞσϧ ҙػߏ͋ΓΤʔδΣϯτ otgt o1 %FDPEFS &ODPEFS m1 m2 m3 "UUFOUJPO
"UUFOUJPO m0 m1 m2 m1 m2 m3 Speaker Listener ϝοηʔδΦϒδΣΫτ ߹கείΞ - ҙػߏ͋Γ - ΦϒδΣΫτෳͷϕΫτϧͰදݱ͞ΕΔ
ҙػߏ͋Γ/ͳ͠ΤʔδΣϯτͷൺֱ - ҙػߏ͋Γͩͱߏੑͷई (TopSim) ্͕͢Δ ҙػߏ͋ΓΤʔδΣϯτͷݴޠͷௐࠪ ࣮ݧͨ͜͠ͱ
ҙػߏ͋Γ/ͳ͠ΤʔδΣϯτͷൺֱ ܇࿅ηοτͷਖ਼ղ ධՁηοτͷਖ਼ղ TopSimʢߏੑͷईʣ - ҙػߏ͕͋Δํ͕ਖ਼ղ͕ߴ͘ͳΔʹ͋Δ - ҙػߏ͕͋Δํ͕ɺTopSim ͕ߴ͘ͳΔʹ͋Δ
ҙػߏ͋ΓΤʔδΣϯτͷ ҙػߏͷՄࢹԽ Speaker Listener Speaker Listener Speaker Listener ޭͨ͠ύλʔϯ ޭͨ͠ύλʔϯ
ࣦഊͨ͠ύλʔϯ
ҙػߏ͋ΓΤʔδΣϯτͷ ൃͨ͠ݴޠͷγϯϘϧͱΦϒδΣΫτͷରԠ Speaker Listener
ҙػߏ͋ΓΤʔδΣϯτͷ ൃͨ͠ݴޠͷγϯϘϧͱΦϒδΣΫτͷରԠ Speaker Listener ্ணܥͷΦϒδΣΫτ ۺܥͷΦϒδΣΫτ
ҙػߏ͋ΓSpeaker ͱ Listener ͷ ҙൣғͷͣΕͱਖ਼ղͷؔ ͣΕ͕গͳ͍΄Ͳਖ਼ղ͍͢͠
ͬͨ͜ͱ - ࢦࣔήʔϜͷΤʔδΣϯτʹҙػߏΛ͚ͭΔ - FashionMNIST ͷը૾ΛͬͨࢦࣔήʔϜͰ࣮ݧ ͔ͬͨ͜ͱ - ҙػߏ͕͋Δͱߏੑ͕ߴ͍ݴޠ͕ൃ͍͢͠
- ҙػߏΛ࣋ͬͨΤʔδΣϯτղऍੑͷ͋ΔݴޠΛൃͤ͞ΒΕΔ ·ͱΊ
࣮͏ͪΐͬͱࣗવͰෳࡶͳը૾ΛͬͨࢦࣔήʔϜͰ ͏·͍ͬͯ͘΄͔͕ͬͨ͠ɺֶश͕͔ͬͨ͠ - ෳࡶͳը૾ͩͱղऍෆೳͳҙͷύλʔϯ͔͠؍͞Εͣ ➡︎ ҙػߏ͕ਓؒͷΑ͏ͳબੑΛ͍࣋ͬͯͳ͍͔Βʁ ਓؒͷ࣋ͭೝػೳͱݴޠͷੑ࣭ͷؔ࿈ͳͲ͕ௐΒΕΔͱ ָͦ͠͏ʁ ࠓޙͷൃల