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
200
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
950
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
4.3k
What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary
ryou0634
0
670
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
890
MIROSTAT で意外さを コントロールした文章生成
ryou0634
1
910
Other Decks in Research
See All in Research
[輪講] SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
nk35jk
2
430
実行環境に中立なWebAssemblyライブマイグレーション機構/techtalk-2025spring
chikuwait
0
210
学生向けアンケート<データサイエンティストについて>
datascientistsociety
PRO
0
2.6k
ノンパラメトリック分布表現を用いた位置尤度場周辺化によるRTK-GNSSの整数アンビギュイティ推定
aoki_nosse
0
320
A multimodal data fusion model for accurate and interpretable urban land use mapping with uncertainty analysis
satai
3
210
ことばの意味を計算するしくみ
verypluming
11
2.6k
近似動的計画入門
mickey_kubo
4
950
Transparency to sustain open science infrastructure - Printemps Couperin
mlarrieu
1
170
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
shunk031
11
7.8k
Vision And Languageモデルにおける異なるドメインでの継続事前学習が性能に与える影響の検証 / YANS2024
sansan_randd
1
100
「エージェントって何?」から「実際の開発現場で役立つ考え方やベストプラクティス」まで
mickey_kubo
0
120
作業記憶の発達的特性が言語獲得の臨界期を形成する(NLP2025)
chemical_tree
2
590
Featured
See All Featured
Building a Scalable Design System with Sketch
lauravandoore
462
33k
Rails Girls Zürich Keynote
gr2m
94
14k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
34
3k
Code Reviewing Like a Champion
maltzj
524
40k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
32
5.9k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
Building a Modern Day E-commerce SEO Strategy
aleyda
41
7.3k
We Have a Design System, Now What?
morganepeng
52
7.6k
Navigating Team Friction
lara
186
15k
Large-scale JavaScript Application Architecture
addyosmani
512
110k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
29
1.8k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
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