SlideShare a Scribd company logo
1 of 20
2017-08 Dwango AI Lab. 02017-08 Dwango AI Lab.
Simulating the Usage Acquisition of
Two-Word Sentences with a First- or
Second-Person Subject and Verb
ARAKAWA, Naoya
Dwango AI Laboratory
2017-08-04
BICA 2017
2017-08 Dwango AI Lab. 1
Outline
1. Introduction
2. The Experiment
3. Discussion
4. Conclusion
2017-08 Dwango AI Lab. 2
Introduction
The paper shows:
A simplistic simulated agent can learn
the use of ‘I’ & ‘you’
in two-word (subject-verb) sentences
interacting with a caretaker agent,
while babbling,
observing utterances & behavior,
and obtaining rewards.
2017-08 Dwango AI Lab. 3
Background
• Previous Works
Learning 1st & 2nd person pronouns observing
more than one caretakers’ language use
E.g., Oshima-Takane+, Gold & Scasselati
• Question: Can one learn them from a
single caretaker?
• Answer: Yes (from this experiment)
2017-08 Dwango AI Lab. 4
The Experiment
1. The World
2. The Language
3. The Caretaker
4. The Learner
5. Results
Luca
gira.
An Image…
2017-08 Dwango AI Lab. 5
The World of the Experiment
Two rambling agents
–A Caretaker
Uses the language of the experiment
–A Language Learner
Learns the language
Each knows its & the other’s utterance/action
given in symbolic forms.
(No symbol grounding issue involved here.)
Three kinds of action: {come, go, turn}
2017-08 Dwango AI Lab. 6
The Language
• Two-word Sentences: Subject+Verb
• Subject: {I, You, Luca, Mario}
– Luca: Language Learner
– Mario: Caretaker
• Verb: {come, go, turn}
• A sentence is used:
– To describe
• Utterer’s own action
• The other’s action
– To ‘give instruction’ to the other.
2017-08 Dwango AI Lab. 7
The Caretaker
• Executes action {come, go, turn} randomly
• Describes its action in 2-word sentences
• Or, instructs the learner to act
{come, go, turn} with a 2-word sentence
• Rewards the Learner when:
– Learner describes its own or caretaker’s action
correctly.
– Learner acts following instruction.
2017-08 Dwango AI Lab. 8
Language Learner
Three Modes:
Reaction Mode / Spontaneous Action Mode / Direction Mode
Has
Caretaker
acted or
uttered?
Reaction Mode
Acts & Utters
Reaction Mode
Utters
Random
Spontaneous
Action Mode:
Acts & Utters.
Direction Mode:
Utters. based on ‘internal
representation’ of
Caretaker’s action
No
Only Uttered
Acted
2017-08 Dwango AI Lab. 9
Learner’s Utterance/Action
• Produced with information:
– Mode
– Its own action (in spontaneous action mode)
– Caretaker’s action/utterance (in reaction mode)
• Choice of Subjects, Verbs & Actions
– Reinforced by Rewards
• Given by Caretaker
• Internal Reward: when Caretaker follows direction
– Random choice: Babbling
• Naïve Bayes + Dirichlet Dist.
(dice throwing based on reward average)
2017-08 Dwango AI Lab. 10
Results
• 2,500 interactions between Caretaker &
Learner
• Success rate = reward rate
• After 1,200 interactions, Learner learned
to utter & act at a 90% rate of correctness.
2017-08 Dwango AI Lab. 11
Success rate of Subject Selection
The success rate of the reaction mode was better
since it had more choices than the other modes.
S react
S sp. act.
S direction
2017-08 Dwango AI Lab. 12
Success rate of Action Selection
2017-08 Dwango AI Lab. 13
Example Interaction
LL: Language Learner (Luca), CT: Caretaker (Mario)
Utt. Utterance, Rew.: Reward
The language for utterances is Interlingua (ia).
2017-08 Dwango AI Lab. 14
Discussion & Conclusion
1. The World
2. The Language
3. Learning
Conclusion
2017-08 Dwango AI Lab. 15
Discussion – The Result
The experiment showed:
• One can learn 1st & 2nd person pronouns
from a single caretaker.
• Playing a minimal language game
• Without grounded concept: object, other,
etc…
2017-08 Dwango AI Lab. 16
Discussion – The Language
• Semantics
– Programmed in Caretaker’s Language Use
• Human Language Acquisition
– Learners are only presented examples in
interactions with Caretakers
• Two-word Sentences
– cf. 1 or 2 word sentence period in infants’
language acquisition.
(not always subject-verb, though)
2017-08 Dwango AI Lab. 17
Discussion – Learning
• Approval as Reward
– In human learning: Smiling, etc.
• Internal Reward
– When Caretaker follows Learner’s direction
⇔ Goal Achieved
• Babbling (random choice) was necessary
& reinforced.
• Modes {reaction, spontaneous action, and
direction} could be learned
– But not in the scope of the current experiment
2017-08 Dwango AI Lab. 18
Conclusion
• Related Research
– Language Emergence with Artificial Agents
• Steels, Vogt, Sugita, et al.
• The current experiment is rather learning existing language.
• Further directions
– More realistic experiments would require reference to
actual human language acquisition.
– Symbol grounding problem
– Learning language models
• E.g., LSTM
• Language use as System of choices
cf. Functional Grammar (MAK Halliday)
2017-08 Dwango AI Lab. 19
EOP
Thank you very much for your attention!

More Related Content

Similar to Simulating the Usage Acquisition of Two-Word Sentences with a First- or Second-Person Subject and Verb

Student centred teaching
Student centred teachingStudent centred teaching
Student centred teachingGiusy Fotia
 
Classroom management and learning style
Classroom management and learning styleClassroom management and learning style
Classroom management and learning styleDesi Wijayanti
 
Core Content Coaching Grade 7 Dichotomous Keys 14-15
Core Content Coaching Grade 7 Dichotomous Keys 14-15Core Content Coaching Grade 7 Dichotomous Keys 14-15
Core Content Coaching Grade 7 Dichotomous Keys 14-15raegan_witt-malandruccolo
 
Communicative Approach presentation part2 class activities
Communicative Approach presentation part2 class activitiesCommunicative Approach presentation part2 class activities
Communicative Approach presentation part2 class activitiesJoanne Chen
 
EAPP Q2 - M6_ Gathering Information.pdf
EAPP Q2 - M6_ Gathering Information.pdfEAPP Q2 - M6_ Gathering Information.pdf
EAPP Q2 - M6_ Gathering Information.pdfLeah Condina
 
Capac questioning december 2 2013
Capac questioning december 2 2013Capac questioning december 2 2013
Capac questioning december 2 2013Jennifer Evans
 
Pa final project-bdinelli
Pa final project-bdinelliPa final project-bdinelli
Pa final project-bdinellibethdinelli
 
MATH TEACHING APPROACHES.pptx
MATH TEACHING APPROACHES.pptxMATH TEACHING APPROACHES.pptx
MATH TEACHING APPROACHES.pptxAnaOnez
 
Just In Time Learning Implementing Principles Of Multimodal Processing And Le...
Just In Time Learning Implementing Principles Of Multimodal Processing And Le...Just In Time Learning Implementing Principles Of Multimodal Processing And Le...
Just In Time Learning Implementing Principles Of Multimodal Processing And Le...wacerone
 
Chungnam.u.textbook.alive.
Chungnam.u.textbook.alive.Chungnam.u.textbook.alive.
Chungnam.u.textbook.alive.Aaron Jolly
 
Teaching listening meeting april 2th 2015
Teaching listening meeting april 2th  2015Teaching listening meeting april 2th  2015
Teaching listening meeting april 2th 2015Mr Bounab Samir
 

Similar to Simulating the Usage Acquisition of Two-Word Sentences with a First- or Second-Person Subject and Verb (20)

Student centred teaching
Student centred teachingStudent centred teaching
Student centred teaching
 
Ela look fors
Ela look forsEla look fors
Ela look fors
 
Ela look fors
Ela look forsEla look fors
Ela look fors
 
Ela look fors
Ela look forsEla look fors
Ela look fors
 
Ela look fors
Ela look forsEla look fors
Ela look fors
 
Ela look fors
Ela look forsEla look fors
Ela look fors
 
Capac ela look fors
Capac  ela look forsCapac  ela look fors
Capac ela look fors
 
Task Based Learning
Task Based LearningTask Based Learning
Task Based Learning
 
Classroom management and learning style
Classroom management and learning styleClassroom management and learning style
Classroom management and learning style
 
Core Content Coaching Grade 7 Dichotomous Keys 14-15
Core Content Coaching Grade 7 Dichotomous Keys 14-15Core Content Coaching Grade 7 Dichotomous Keys 14-15
Core Content Coaching Grade 7 Dichotomous Keys 14-15
 
Communicative Approach presentation part2 class activities
Communicative Approach presentation part2 class activitiesCommunicative Approach presentation part2 class activities
Communicative Approach presentation part2 class activities
 
EAPP Q2 - M6_ Gathering Information.pdf
EAPP Q2 - M6_ Gathering Information.pdfEAPP Q2 - M6_ Gathering Information.pdf
EAPP Q2 - M6_ Gathering Information.pdf
 
February 18th presentation
February 18th presentationFebruary 18th presentation
February 18th presentation
 
Capac questioning december 2 2013
Capac questioning december 2 2013Capac questioning december 2 2013
Capac questioning december 2 2013
 
Pa final project-bdinelli
Pa final project-bdinelliPa final project-bdinelli
Pa final project-bdinelli
 
MATH TEACHING APPROACHES.pptx
MATH TEACHING APPROACHES.pptxMATH TEACHING APPROACHES.pptx
MATH TEACHING APPROACHES.pptx
 
Just In Time Learning Implementing Principles Of Multimodal Processing And Le...
Just In Time Learning Implementing Principles Of Multimodal Processing And Le...Just In Time Learning Implementing Principles Of Multimodal Processing And Le...
Just In Time Learning Implementing Principles Of Multimodal Processing And Le...
 
Chungnam.u.textbook.alive.
Chungnam.u.textbook.alive.Chungnam.u.textbook.alive.
Chungnam.u.textbook.alive.
 
Teaching listening meeting april 2th 2015
Teaching listening meeting april 2th  2015Teaching listening meeting april 2th  2015
Teaching listening meeting april 2th 2015
 
Observation.pptx
Observation.pptxObservation.pptx
Observation.pptx
 

More from Naoya Arakawa

Information Binding with Dynamic Associative Representations
Information Binding with Dynamic Associative RepresentationsInformation Binding with Dynamic Associative Representations
Information Binding with Dynamic Associative RepresentationsNaoya Arakawa
 
汎用人工知能について(2015-12)
汎用人工知能について(2015-12)汎用人工知能について(2015-12)
汎用人工知能について(2015-12)Naoya Arakawa
 
自由意志の問題を「ふりかえる」
自由意志の問題を「ふりかえる」自由意志の問題を「ふりかえる」
自由意志の問題を「ふりかえる」Naoya Arakawa
 
認知科学会サマースクール2015・人工知能と言語機能
認知科学会サマースクール2015・人工知能と言語機能認知科学会サマースクール2015・人工知能と言語機能
認知科学会サマースクール2015・人工知能と言語機能Naoya Arakawa
 
Human-Level AI & Phenomenology
Human-Level AI & PhenomenologyHuman-Level AI & Phenomenology
Human-Level AI & PhenomenologyNaoya Arakawa
 
ヒト並みの人工知能と現象学
ヒト並みの人工知能と現象学ヒト並みの人工知能と現象学
ヒト並みの人工知能と現象学Naoya Arakawa
 
汎用人工知能の研究動向
汎用人工知能の研究動向汎用人工知能の研究動向
汎用人工知能の研究動向Naoya Arakawa
 

More from Naoya Arakawa (7)

Information Binding with Dynamic Associative Representations
Information Binding with Dynamic Associative RepresentationsInformation Binding with Dynamic Associative Representations
Information Binding with Dynamic Associative Representations
 
汎用人工知能について(2015-12)
汎用人工知能について(2015-12)汎用人工知能について(2015-12)
汎用人工知能について(2015-12)
 
自由意志の問題を「ふりかえる」
自由意志の問題を「ふりかえる」自由意志の問題を「ふりかえる」
自由意志の問題を「ふりかえる」
 
認知科学会サマースクール2015・人工知能と言語機能
認知科学会サマースクール2015・人工知能と言語機能認知科学会サマースクール2015・人工知能と言語機能
認知科学会サマースクール2015・人工知能と言語機能
 
Human-Level AI & Phenomenology
Human-Level AI & PhenomenologyHuman-Level AI & Phenomenology
Human-Level AI & Phenomenology
 
ヒト並みの人工知能と現象学
ヒト並みの人工知能と現象学ヒト並みの人工知能と現象学
ヒト並みの人工知能と現象学
 
汎用人工知能の研究動向
汎用人工知能の研究動向汎用人工知能の研究動向
汎用人工知能の研究動向
 

Recently uploaded

Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsSérgio Sacani
 
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)Joonhun Lee
 
pumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit flypumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit flyPRADYUMMAURYA1
 
Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Silpa
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and ClassificationsAreesha Ahmad
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformationAreesha Ahmad
 
Unit5-Cloud.pptx for lpu course cse121 o
Unit5-Cloud.pptx for lpu course cse121 oUnit5-Cloud.pptx for lpu course cse121 o
Unit5-Cloud.pptx for lpu course cse121 oManavSingh202607
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000Sapana Sha
 
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...Monika Rani
 
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptxSCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptxRizalinePalanog2
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksSérgio Sacani
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPirithiRaju
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)Areesha Ahmad
 
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts ServiceJustdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Servicemonikaservice1
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)Areesha Ahmad
 
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑Damini Dixit
 
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...chandars293
 
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.Nitya salvi
 
COST ESTIMATION FOR A RESEARCH PROJECT.pptx
COST ESTIMATION FOR A RESEARCH PROJECT.pptxCOST ESTIMATION FOR A RESEARCH PROJECT.pptx
COST ESTIMATION FOR A RESEARCH PROJECT.pptxFarihaAbdulRasheed
 

Recently uploaded (20)

Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
 
pumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit flypumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit fly
 
Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and Classifications
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
 
Unit5-Cloud.pptx for lpu course cse121 o
Unit5-Cloud.pptx for lpu course cse121 oUnit5-Cloud.pptx for lpu course cse121 o
Unit5-Cloud.pptx for lpu course cse121 o
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
 
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
 
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptxSCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)
 
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts ServiceJustdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)
 
Site Acceptance Test .
Site Acceptance Test                    .Site Acceptance Test                    .
Site Acceptance Test .
 
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
 
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
 
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
 
COST ESTIMATION FOR A RESEARCH PROJECT.pptx
COST ESTIMATION FOR A RESEARCH PROJECT.pptxCOST ESTIMATION FOR A RESEARCH PROJECT.pptx
COST ESTIMATION FOR A RESEARCH PROJECT.pptx
 

Simulating the Usage Acquisition of Two-Word Sentences with a First- or Second-Person Subject and Verb

  • 1. 2017-08 Dwango AI Lab. 02017-08 Dwango AI Lab. Simulating the Usage Acquisition of Two-Word Sentences with a First- or Second-Person Subject and Verb ARAKAWA, Naoya Dwango AI Laboratory 2017-08-04 BICA 2017
  • 2. 2017-08 Dwango AI Lab. 1 Outline 1. Introduction 2. The Experiment 3. Discussion 4. Conclusion
  • 3. 2017-08 Dwango AI Lab. 2 Introduction The paper shows: A simplistic simulated agent can learn the use of ‘I’ & ‘you’ in two-word (subject-verb) sentences interacting with a caretaker agent, while babbling, observing utterances & behavior, and obtaining rewards.
  • 4. 2017-08 Dwango AI Lab. 3 Background • Previous Works Learning 1st & 2nd person pronouns observing more than one caretakers’ language use E.g., Oshima-Takane+, Gold & Scasselati • Question: Can one learn them from a single caretaker? • Answer: Yes (from this experiment)
  • 5. 2017-08 Dwango AI Lab. 4 The Experiment 1. The World 2. The Language 3. The Caretaker 4. The Learner 5. Results Luca gira. An Image…
  • 6. 2017-08 Dwango AI Lab. 5 The World of the Experiment Two rambling agents –A Caretaker Uses the language of the experiment –A Language Learner Learns the language Each knows its & the other’s utterance/action given in symbolic forms. (No symbol grounding issue involved here.) Three kinds of action: {come, go, turn}
  • 7. 2017-08 Dwango AI Lab. 6 The Language • Two-word Sentences: Subject+Verb • Subject: {I, You, Luca, Mario} – Luca: Language Learner – Mario: Caretaker • Verb: {come, go, turn} • A sentence is used: – To describe • Utterer’s own action • The other’s action – To ‘give instruction’ to the other.
  • 8. 2017-08 Dwango AI Lab. 7 The Caretaker • Executes action {come, go, turn} randomly • Describes its action in 2-word sentences • Or, instructs the learner to act {come, go, turn} with a 2-word sentence • Rewards the Learner when: – Learner describes its own or caretaker’s action correctly. – Learner acts following instruction.
  • 9. 2017-08 Dwango AI Lab. 8 Language Learner Three Modes: Reaction Mode / Spontaneous Action Mode / Direction Mode Has Caretaker acted or uttered? Reaction Mode Acts & Utters Reaction Mode Utters Random Spontaneous Action Mode: Acts & Utters. Direction Mode: Utters. based on ‘internal representation’ of Caretaker’s action No Only Uttered Acted
  • 10. 2017-08 Dwango AI Lab. 9 Learner’s Utterance/Action • Produced with information: – Mode – Its own action (in spontaneous action mode) – Caretaker’s action/utterance (in reaction mode) • Choice of Subjects, Verbs & Actions – Reinforced by Rewards • Given by Caretaker • Internal Reward: when Caretaker follows direction – Random choice: Babbling • Naïve Bayes + Dirichlet Dist. (dice throwing based on reward average)
  • 11. 2017-08 Dwango AI Lab. 10 Results • 2,500 interactions between Caretaker & Learner • Success rate = reward rate • After 1,200 interactions, Learner learned to utter & act at a 90% rate of correctness.
  • 12. 2017-08 Dwango AI Lab. 11 Success rate of Subject Selection The success rate of the reaction mode was better since it had more choices than the other modes. S react S sp. act. S direction
  • 13. 2017-08 Dwango AI Lab. 12 Success rate of Action Selection
  • 14. 2017-08 Dwango AI Lab. 13 Example Interaction LL: Language Learner (Luca), CT: Caretaker (Mario) Utt. Utterance, Rew.: Reward The language for utterances is Interlingua (ia).
  • 15. 2017-08 Dwango AI Lab. 14 Discussion & Conclusion 1. The World 2. The Language 3. Learning Conclusion
  • 16. 2017-08 Dwango AI Lab. 15 Discussion – The Result The experiment showed: • One can learn 1st & 2nd person pronouns from a single caretaker. • Playing a minimal language game • Without grounded concept: object, other, etc…
  • 17. 2017-08 Dwango AI Lab. 16 Discussion – The Language • Semantics – Programmed in Caretaker’s Language Use • Human Language Acquisition – Learners are only presented examples in interactions with Caretakers • Two-word Sentences – cf. 1 or 2 word sentence period in infants’ language acquisition. (not always subject-verb, though)
  • 18. 2017-08 Dwango AI Lab. 17 Discussion – Learning • Approval as Reward – In human learning: Smiling, etc. • Internal Reward – When Caretaker follows Learner’s direction ⇔ Goal Achieved • Babbling (random choice) was necessary & reinforced. • Modes {reaction, spontaneous action, and direction} could be learned – But not in the scope of the current experiment
  • 19. 2017-08 Dwango AI Lab. 18 Conclusion • Related Research – Language Emergence with Artificial Agents • Steels, Vogt, Sugita, et al. • The current experiment is rather learning existing language. • Further directions – More realistic experiments would require reference to actual human language acquisition. – Symbol grounding problem – Learning language models • E.g., LSTM • Language use as System of choices cf. Functional Grammar (MAK Halliday)
  • 20. 2017-08 Dwango AI Lab. 19 EOP Thank you very much for your attention!