SlideShare uma empresa Scribd logo

Simulation of Language Acquisition Walter Daelemans

•Transferir como PPT, PDF•
•
B
butest
1 de 81
Simulation of Language Acquisition Walter Daelemans (CNTS, University of Antwerp) [email_address] http://www.cnts.ua.ac.be/~walter EMLAR 2005 Utrecht
Overview ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Simulation (1) ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Simulation (2) ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Machine Learning as a model for acquisition ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Output Input Performance Component R i R k R l R j Learning Component Search Experience BIAS
Generalisation  Abstraction + abstraction - abstraction + generalisation - generalisation Rule Induction Connectionism Statistics Handcrafting Table Lookup Memory-Based Learning … (Fill in your most hated linguist here)
Nativism  Rule-Based nativist empiricist + rule-based - rule-based Innate mental rules Rule Induction Connectionism Statistics Memory-Based Learning Hard-wired neural networks Innate probabilities? Innate exemplars?
Machine Learning crash course ,[object Object],[object Object],[object Object],[object Object],[object Object]
Machine Learning: Roots ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Machine Learning: 2 types ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Empirical ML: Key Terms 1 ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Empirical ML: Key Terms 2 ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Empirical ML: 2 Flavors ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Eager vs Lazy Learning ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
-etje -kje Coda last syl Nucleus last syl Rule Induction
? -etje -kje Coda last syl Nucleus last syl MBL
Eager vs Lazy Learning ,[object Object],[object Object],[object Object],[object Object],[object Object]
Eager vs Lazy Learning ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Eager vs Lazy: So? ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
 
ML and Natural Language ,[object Object],[object Object],[object Object],[object Object]
Case Study Exemplar-based acquisition of Dutch Stress (Durieux / Gillis / Daelemans)
This “rule of nearest neighbor” has considerable elementary intuitive appeal and probably corresponds to practice in many situations. For example, it is possible that much medical diagnosis is influenced by the doctor's recollection of the subsequent history of an earlier patient whose symptoms resemble in some way those of the current patient. (Fix and Hodges, 1952, p.43) MBL: Use memory traces of experiences as a basis for analogical reasoning, rather than using rules or other abstractions extracted from experience and replacing the experiences.
MBL Acquisition ,[object Object],[object Object],[object Object],[object Object],[object Object]
MBL Processing ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Operationalization ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
The Overlap distance function ,[object Object]
The MVDM distance function ,[object Object],[object Object],[object Object]
Feature weighting in the distance function ,[object Object],[object Object]
Entropy & IG: Formulas
Exemplar weighting ,[object Object],[object Object],[object Object]
Distance weighting ,[object Object],[object Object],[object Object],[object Object],[object Object]
Learning word stress: A case study ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
MBL for psychology ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Dominant Linguistic Approach ,[object Object],[object Object],[object Object],[object Object],[object Object]
YOUPIE (Dresher & Kaye, 1990) ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
   1 0 1 0 0 0 0 1 1 0 1 UG-stress Grammar and Assignment rules word PLD Cue-based Learning
Parameters (with setting for Dutch) Feet are / aren’t assigned iteratively P10 Weak foot looses / doesn’t loose foot status in a clash P9 Left / Right -most syllable is extra-metrical P8 There isn’t / is an extra-metrical syllable P8A Strong node in foot must / mustn’t branch P7 Feet are quantity-sensitive w.r.t. rime / nucleus P6 Feet are / are not quantity-sensitive P5 Feet right/ left -dominant P4 Feet assigned from the left/ right edge P3 Binary/ unbound feet P2 Word tree right /left dominant P1 Value Parameter
MBL ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Syllable-structure representations Retrieval or Similarity-based reasoning on exemplars word PLD Storage Stress pattern
YOUPIE tested ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
MBLP vs. Youpie 81% 176 YOUPIE-languages 41% 89 MBLP-languages 95% 11.88 YOUPIE-syllables 97% 3.7 MBLP-syllables 90% 28.24 105 YOUPIE-words 89% 15.01 104 MBLP-words Accuracy Sd Score System and level
Discussion ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Dutch stress ,[object Object],[object Object],[object Object],[object Object]
MBLP on Dutch data ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Results
Language Acquisition ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Error Percentages
Discussion ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Adult processing ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Experimental set-up ,[object Object],[object Object],[object Object],60 60 Irregulars 60 60 Regulars Trisyllabic Bisyllabic
Experimental set-up ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Results
Results
Discussion ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Summary ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Overall Conclusion ,[object Object],[object Object],[object Object],[object Object],[object Object]
Simulation with TiMBL Demonstration: German plural
TiMBL http://ilk.uvt.nl/timbl ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Current practice ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Data & Representation ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Cognitive Architectures of Inflectional Morphology ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Dual Route Pattern Associator Rule Input Features Suffix-class Memory Failure
German Plural ,[object Object],[object Object],[object Object],[object Object]
 
The default status of -s ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
 
Discussion ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],*,*,*,*,i,r,M e
 
 
Acquisition Data: Summary of previous studies ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
MBLP simulation ,[object Object],[object Object],[object Object]
Bartke, Marcus, Clahsen (1995) ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
MBLP simulation ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Conclusions ,[object Object],[object Object],[object Object]

Recomendados

Practical deepllearningv1
Practical deepllearningv1Practical deepllearningv1
Practical deepllearningv1arthi v
 
Deep Learning for Search
Deep Learning for SearchDeep Learning for Search
Deep Learning for SearchBhaskar Mitra
 
A Simple Introduction to Neural Information Retrieval
A Simple Introduction to Neural Information RetrievalA Simple Introduction to Neural Information Retrieval
A Simple Introduction to Neural Information RetrievalBhaskar Mitra
 
Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Bhaskar Mitra
 
CMSC 723: Computational Linguistics I
CMSC 723: Computational Linguistics ICMSC 723: Computational Linguistics I
CMSC 723: Computational Linguistics Ibutest
 
Introduction to Machine Learning.
Introduction to Machine Learning.Introduction to Machine Learning.
Introduction to Machine Learning.butest
 
Basic review on topic modeling
Basic review on topic modelingBasic review on topic modeling
Basic review on topic modelingHiroyuki Kuromiya
 
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingTed Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingMLconf
 

Recomendados

Practical deepllearningv1
Practical deepllearningv1Practical deepllearningv1
Practical deepllearningv1arthi v
 
Deep Learning for Search
Deep Learning for SearchDeep Learning for Search
Deep Learning for SearchBhaskar Mitra
 
A Simple Introduction to Neural Information Retrieval
A Simple Introduction to Neural Information RetrievalA Simple Introduction to Neural Information Retrieval
A Simple Introduction to Neural Information RetrievalBhaskar Mitra
 
Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Bhaskar Mitra
 
CMSC 723: Computational Linguistics I
CMSC 723: Computational Linguistics ICMSC 723: Computational Linguistics I
CMSC 723: Computational Linguistics Ibutest
 
Introduction to Machine Learning.
Introduction to Machine Learning.Introduction to Machine Learning.
Introduction to Machine Learning.butest
 
Basic review on topic modeling
Basic review on topic modelingBasic review on topic modeling
Basic review on topic modelingHiroyuki Kuromiya
 
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingTed Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingMLconf
 
Topics Modeling
Topics ModelingTopics Modeling
Topics ModelingSvitlana volkova
 
Deep Neural Methods for Retrieval
Deep Neural Methods for RetrievalDeep Neural Methods for Retrieval
Deep Neural Methods for RetrievalBhaskar Mitra
 
Neural Models for Information Retrieval
Neural Models for Information RetrievalNeural Models for Information Retrieval
Neural Models for Information RetrievalBhaskar Mitra
 
Multilingual Text Classification using Ontologies
Multilingual Text Classification using OntologiesMultilingual Text Classification using Ontologies
Multilingual Text Classification using OntologiesGerard de Melo
 
Topic Modeling
Topic ModelingTopic Modeling
Topic ModelingKarol Grzegorczyk
 
2008 Memory Revision
2008 Memory Revision2008 Memory Revision
2008 Memory Revisionjillfitz
 
Topicmodels
TopicmodelsTopicmodels
TopicmodelsAjay Ohri
 
Canini09a
Canini09aCanini09a
Canini09aAjay Ohri
 
Convolutional neural networks for sentiment classification
Convolutional neural networks for sentiment classificationConvolutional neural networks for sentiment classification
Convolutional neural networks for sentiment classificationYunchao He
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningOswald Campesato
 
Latent Dirichlet Allocation
Latent Dirichlet AllocationLatent Dirichlet Allocation
Latent Dirichlet AllocationMarco Righini
 
Main single agent machine learning algorithms
Main single agent machine learning algorithmsMain single agent machine learning algorithms
Main single agent machine learning algorithmsbutest
 
Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)
Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)
Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)Márton Miháltz
 
Lifelong Topic Modelling presentation
Lifelong Topic Modelling presentation Lifelong Topic Modelling presentation
Lifelong Topic Modelling presentation Daniele Di Mitri
 
Multi-label, Multi-class Classification Using Polylingual Embeddings
Multi-label, Multi-class Classification Using Polylingual EmbeddingsMulti-label, Multi-class Classification Using Polylingual Embeddings
Multi-label, Multi-class Classification Using Polylingual EmbeddingsGeorge Balikas
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningAmr Rashed
 
Topic models
Topic modelsTopic models
Topic modelsAjay Ohri
 
[PDF]
[PDF][PDF]
[PDF]butest
 
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...Association for Computational Linguistics
 
Email
EmailEmail
EmailShashwat Shriparv
 
History of simulation software
History of simulation softwareHistory of simulation software
History of simulation softwareShashwat Shriparv
 
D&B ArrayProcessing Introductory Brochure_EN.PDF
D&B ArrayProcessing Introductory Brochure_EN.PDFD&B ArrayProcessing Introductory Brochure_EN.PDF
D&B ArrayProcessing Introductory Brochure_EN.PDFLiam Halpin
 

Mais conteúdo relacionado

Mais procurados

Deep Neural Methods for Retrieval
Deep Neural Methods for RetrievalDeep Neural Methods for Retrieval
Deep Neural Methods for RetrievalBhaskar Mitra
 
Neural Models for Information Retrieval
Neural Models for Information RetrievalNeural Models for Information Retrieval
Neural Models for Information RetrievalBhaskar Mitra
 
Multilingual Text Classification using Ontologies
Multilingual Text Classification using OntologiesMultilingual Text Classification using Ontologies
Multilingual Text Classification using OntologiesGerard de Melo
 
2008 Memory Revision
2008 Memory Revision2008 Memory Revision
2008 Memory Revisionjillfitz
 
Convolutional neural networks for sentiment classification
Convolutional neural networks for sentiment classificationConvolutional neural networks for sentiment classification
Convolutional neural networks for sentiment classificationYunchao He
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningOswald Campesato
 
Latent Dirichlet Allocation
Latent Dirichlet AllocationLatent Dirichlet Allocation
Latent Dirichlet AllocationMarco Righini
 
Main single agent machine learning algorithms
Main single agent machine learning algorithmsMain single agent machine learning algorithms
Main single agent machine learning algorithmsbutest
 
Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)
Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)
Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)Márton Miháltz
 
Lifelong Topic Modelling presentation
Lifelong Topic Modelling presentation Lifelong Topic Modelling presentation
Lifelong Topic Modelling presentation Daniele Di Mitri
 
Multi-label, Multi-class Classification Using Polylingual Embeddings
Multi-label, Multi-class Classification Using Polylingual EmbeddingsMulti-label, Multi-class Classification Using Polylingual Embeddings
Multi-label, Multi-class Classification Using Polylingual EmbeddingsGeorge Balikas
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningAmr Rashed
 
Topic models
Topic modelsTopic models
Topic modelsAjay Ohri
 
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...Association for Computational Linguistics
 

Mais procurados (19)

Topics Modeling
Topics ModelingTopics Modeling
Topics Modeling
 
Deep Neural Methods for Retrieval
Deep Neural Methods for RetrievalDeep Neural Methods for Retrieval
Deep Neural Methods for Retrieval
 
Neural Models for Information Retrieval
Neural Models for Information RetrievalNeural Models for Information Retrieval
Neural Models for Information Retrieval
 
Multilingual Text Classification using Ontologies
Multilingual Text Classification using OntologiesMultilingual Text Classification using Ontologies
Multilingual Text Classification using Ontologies
 
Topic Modeling
Topic ModelingTopic Modeling
Topic Modeling
 
2008 Memory Revision
2008 Memory Revision2008 Memory Revision
2008 Memory Revision
 
Topicmodels
TopicmodelsTopicmodels
Topicmodels
 
Canini09a
Canini09aCanini09a
Canini09a
 
Convolutional neural networks for sentiment classification
Convolutional neural networks for sentiment classificationConvolutional neural networks for sentiment classification
Convolutional neural networks for sentiment classification
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
Latent Dirichlet Allocation
Latent Dirichlet AllocationLatent Dirichlet Allocation
Latent Dirichlet Allocation
 
Main single agent machine learning algorithms
Main single agent machine learning algorithmsMain single agent machine learning algorithms
Main single agent machine learning algorithms
 
Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)
Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)
Deep Learning Architectures for NLP (Hungarian NLP Meetup 2016-09-07)
 
Lifelong Topic Modelling presentation
Lifelong Topic Modelling presentation Lifelong Topic Modelling presentation
Lifelong Topic Modelling presentation
 
Multi-label, Multi-class Classification Using Polylingual Embeddings
Multi-label, Multi-class Classification Using Polylingual EmbeddingsMulti-label, Multi-class Classification Using Polylingual Embeddings
Multi-label, Multi-class Classification Using Polylingual Embeddings
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Topic models
Topic modelsTopic models
Topic models
 
[PDF]
[PDF][PDF]
[PDF]
 
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
 

Destaque

History of simulation software
History of simulation softwareHistory of simulation software
History of simulation softwareShashwat Shriparv
 
D&B ArrayProcessing Introductory Brochure_EN.PDF
D&B ArrayProcessing Introductory Brochure_EN.PDFD&B ArrayProcessing Introductory Brochure_EN.PDF
D&B ArrayProcessing Introductory Brochure_EN.PDFLiam Halpin
 
Agena adsif – a language for simulation & agent
Agena adsif – a language for simulation & agentAgena adsif – a language for simulation & agent
Agena adsif – a language for simulation & agentMehmet Fatih Hocaoglu
 
General purpose simulation System (GPSS)
General purpose simulation System (GPSS)General purpose simulation System (GPSS)
General purpose simulation System (GPSS)Tushar Aneyrao
 
Application of simulation in anesthesia Application of simulation in anesth...
Application of simulation in anesthesia Application of simulation in anesth...Application of simulation in anesthesia Application of simulation in anesth...
Application of simulation in anesthesia Application of simulation in anesth...MedicineAndHealth
 
Steps in Simulation Study
Steps in Simulation StudySteps in Simulation Study
Steps in Simulation StudyNalin Adhikari
 
Chp. 2 simulation examples
Chp. 2 simulation examplesChp. 2 simulation examples
Chp. 2 simulation examplesPravesh Negi
 
System simulation & modeling notes[sjbit]
System simulation & modeling notes[sjbit]System simulation & modeling notes[sjbit]
System simulation & modeling notes[sjbit]qwerty626
 
Introduction to Simulation
Introduction to SimulationIntroduction to Simulation
Introduction to Simulationchimco.net
 
Simulation of Wireless Communication Systems
Simulation of Wireless Communication SystemsSimulation of Wireless Communication Systems
Simulation of Wireless Communication SystemsBernd-Peter Paris
 

Destaque (16)

Email
EmailEmail
Email
 
History of simulation software
History of simulation softwareHistory of simulation software
History of simulation software
 
D&B ArrayProcessing Introductory Brochure_EN.PDF
D&B ArrayProcessing Introductory Brochure_EN.PDFD&B ArrayProcessing Introductory Brochure_EN.PDF
D&B ArrayProcessing Introductory Brochure_EN.PDF
 
S.C.A.M. Present SOUNDSCAPE
S.C.A.M. Present SOUNDSCAPES.C.A.M. Present SOUNDSCAPE
S.C.A.M. Present SOUNDSCAPE
 
Agena adsif – a language for simulation & agent
Agena adsif – a language for simulation & agentAgena adsif – a language for simulation & agent
Agena adsif – a language for simulation & agent
 
eEngineering 2009—2012. Digitising the product process
eEngineering 2009—2012. Digitising the product processeEngineering 2009—2012. Digitising the product process
eEngineering 2009—2012. Digitising the product process
 
General purpose simulation System (GPSS)
General purpose simulation System (GPSS)General purpose simulation System (GPSS)
General purpose simulation System (GPSS)
 
Application of simulation in anesthesia Application of simulation in anesth...
Application of simulation in anesthesia Application of simulation in anesth...Application of simulation in anesthesia Application of simulation in anesth...
Application of simulation in anesthesia Application of simulation in anesth...
 
Steps in Simulation Study
Steps in Simulation StudySteps in Simulation Study
Steps in Simulation Study
 
Virtual Reality
Virtual RealityVirtual Reality
Virtual Reality
 
Modelling and simulation
Modelling and simulationModelling and simulation
Modelling and simulation
 
Chp. 2 simulation examples
Chp. 2 simulation examplesChp. 2 simulation examples
Chp. 2 simulation examples
 
System simulation & modeling notes[sjbit]
System simulation & modeling notes[sjbit]System simulation & modeling notes[sjbit]
System simulation & modeling notes[sjbit]
 
Introduction to Simulation
Introduction to SimulationIntroduction to Simulation
Introduction to Simulation
 
Simulation of Wireless Communication Systems
Simulation of Wireless Communication SystemsSimulation of Wireless Communication Systems
Simulation of Wireless Communication Systems
 
Slideshare ppt
Slideshare pptSlideshare ppt
Slideshare ppt
 

Semelhante a Simulation of Language Acquisition Walter Daelemans

ppt slides
ppt slidesppt slides
ppt slidesbutest
 
Machine Learning for NLP
Machine Learning for NLPMachine Learning for NLP
Machine Learning for NLPbutest
 
lecture_mooney.ppt
lecture_mooney.pptlecture_mooney.ppt
lecture_mooney.pptbutest
 
The Geometry of Learning
The Geometry of LearningThe Geometry of Learning
The Geometry of Learningfridolin.wild
 
Artificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and OverviewArtificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and Overviewbutest
 
Artificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and OverviewArtificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and Overviewbutest
 
slides
slidesslides
slidesbutest
 
slides
slidesslides
slidesbutest
 
SNLI_presentation_2
SNLI_presentation_2SNLI_presentation_2
SNLI_presentation_2Viral Gupta
 
Lecture 01: Machine Learning for Language Technology - Introduction
Lecture 01: Machine Learning for Language Technology - Introduction Lecture 01: Machine Learning for Language Technology - Introduction
Lecture 01: Machine Learning for Language Technology - IntroductionMarina Santini
 
Machine Learning: Foundations Course Number 0368403401
Machine Learning: Foundations Course Number 0368403401Machine Learning: Foundations Course Number 0368403401
Machine Learning: Foundations Course Number 0368403401butest
 
Machine Learning
Machine LearningMachine Learning
Machine Learningbutest
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.pptbutest
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.pptbutest
 
Presentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data MiningPresentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data Miningbutest
 
kantorNSF-NIJ-ISI-03-06-04.ppt
kantorNSF-NIJ-ISI-03-06-04.pptkantorNSF-NIJ-ISI-03-06-04.ppt
kantorNSF-NIJ-ISI-03-06-04.pptbutest
 
Learning, Logic, and Probability: a Unified View
Learning, Logic, and Probability: a Unified ViewLearning, Logic, and Probability: a Unified View
Learning, Logic, and Probability: a Unified Viewbutest
 

Semelhante a Simulation of Language Acquisition Walter Daelemans (20)

ppt slides
ppt slidesppt slides
ppt slides
 
Machine Learning for NLP
Machine Learning for NLPMachine Learning for NLP
Machine Learning for NLP
 
lecture_mooney.ppt
lecture_mooney.pptlecture_mooney.ppt
lecture_mooney.ppt
 
Eric Smidth
Eric SmidthEric Smidth
Eric Smidth
 
The Geometry of Learning
The Geometry of LearningThe Geometry of Learning
The Geometry of Learning
 
Artificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and OverviewArtificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and Overview
 
Artificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and OverviewArtificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and Overview
 
ppt
pptppt
ppt
 
slides
slidesslides
slides
 
slides
slidesslides
slides
 
SNLI_presentation_2
SNLI_presentation_2SNLI_presentation_2
SNLI_presentation_2
 
Lecture 01: Machine Learning for Language Technology - Introduction
Lecture 01: Machine Learning for Language Technology - Introduction Lecture 01: Machine Learning for Language Technology - Introduction
Lecture 01: Machine Learning for Language Technology - Introduction
 
Machine Learning: Foundations Course Number 0368403401
Machine Learning: Foundations Course Number 0368403401Machine Learning: Foundations Course Number 0368403401
Machine Learning: Foundations Course Number 0368403401
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.ppt
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.ppt
 
Presentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data MiningPresentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data Mining
 
kantorNSF-NIJ-ISI-03-06-04.ppt
kantorNSF-NIJ-ISI-03-06-04.pptkantorNSF-NIJ-ISI-03-06-04.ppt
kantorNSF-NIJ-ISI-03-06-04.ppt
 
Equirs: Explicitly Query Understanding Information Retrieval System Based on Hmm
Equirs: Explicitly Query Understanding Information Retrieval System Based on HmmEquirs: Explicitly Query Understanding Information Retrieval System Based on Hmm
Equirs: Explicitly Query Understanding Information Retrieval System Based on Hmm
 
Learning, Logic, and Probability: a Unified View
Learning, Logic, and Probability: a Unified ViewLearning, Logic, and Probability: a Unified View
Learning, Logic, and Probability: a Unified View
 

Mais de butest

EL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBEEL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBEbutest
 
1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同butest
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALbutest
 
Timeline: The Life of Michael Jackson
Timeline: The Life of Michael JacksonTimeline: The Life of Michael Jackson
Timeline: The Life of Michael Jacksonbutest
 
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...butest
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALbutest
 
Com 380, Summer II
Com 380, Summer IICom 380, Summer II
Com 380, Summer IIbutest
 
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet JazzThe MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazzbutest
 
MICHAEL JACKSON.doc
MICHAEL JACKSON.docMICHAEL JACKSON.doc
MICHAEL JACKSON.docbutest
 
Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1butest
 
Facebook
Facebook Facebook
Facebook butest
 
Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...butest
 
Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...butest
 
NEWS ANNOUNCEMENT
NEWS ANNOUNCEMENTNEWS ANNOUNCEMENT
NEWS ANNOUNCEMENTbutest
 
C-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.docC-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.docbutest
 
MAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.docMAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.docbutest
 
Mac OS X Guide.doc
Mac OS X Guide.docMac OS X Guide.doc
Mac OS X Guide.docbutest
 
WEB DESIGN!
WEB DESIGN!WEB DESIGN!
WEB DESIGN!butest
 

Mais de butest (20)

EL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBEEL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBE
 
1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIAL
 
Timeline: The Life of Michael Jackson
Timeline: The Life of Michael JacksonTimeline: The Life of Michael Jackson
Timeline: The Life of Michael Jackson
 
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIAL
 
Com 380, Summer II
Com 380, Summer IICom 380, Summer II
Com 380, Summer II
 
PPT
PPTPPT
PPT
 
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet JazzThe MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
 
MICHAEL JACKSON.doc
MICHAEL JACKSON.docMICHAEL JACKSON.doc
MICHAEL JACKSON.doc
 
Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1
 
Facebook
Facebook Facebook
Facebook
 
Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...
 
Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...
 
NEWS ANNOUNCEMENT
NEWS ANNOUNCEMENTNEWS ANNOUNCEMENT
NEWS ANNOUNCEMENT
 
C-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.docC-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.doc
 
MAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.docMAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.doc
 
Mac OS X Guide.doc
Mac OS X Guide.docMac OS X Guide.doc
Mac OS X Guide.doc
 
hier
hierhier
hier
 
WEB DESIGN!
WEB DESIGN!WEB DESIGN!
WEB DESIGN!
 

Simulation of Language Acquisition Walter Daelemans

  • 1. Simulation of Language Acquisition Walter Daelemans (CNTS, University of Antwerp) [email_address] http://www.cnts.ua.ac.be/~walter EMLAR 2005 Utrecht
  • 2.
  • 3.
  • 4.
  • 5.
  • 6. Output Input Performance Component R i R k R l R j Learning Component Search Experience BIAS
  • 7. Generalisation  Abstraction + abstraction - abstraction + generalisation - generalisation Rule Induction Connectionism Statistics Handcrafting Table Lookup Memory-Based Learning … (Fill in your most hated linguist here)
  • 8. Nativism  Rule-Based nativist empiricist + rule-based - rule-based Innate mental rules Rule Induction Connectionism Statistics Memory-Based Learning Hard-wired neural networks Innate probabilities? Innate exemplars?
  • 9.
  • 10.
  • 11.
  • 12.
  • 13.
  • 14.
  • 15.
  • 16. -etje -kje Coda last syl Nucleus last syl Rule Induction
  • 17. ? -etje -kje Coda last syl Nucleus last syl MBL
  • 18.
  • 19.
  • 20.
  • 21.  
  • 22.
  • 23. Case Study Exemplar-based acquisition of Dutch Stress (Durieux / Gillis / Daelemans)
  • 24. This “rule of nearest neighbor” has considerable elementary intuitive appeal and probably corresponds to practice in many situations. For example, it is possible that much medical diagnosis is influenced by the doctor's recollection of the subsequent history of an earlier patient whose symptoms resemble in some way those of the current patient. (Fix and Hodges, 1952, p.43) MBL: Use memory traces of experiences as a basis for analogical reasoning, rather than using rules or other abstractions extracted from experience and replacing the experiences.
  • 25.
  • 26.
  • 27.
  • 28.
  • 29.
  • 30.
  • 31. Entropy & IG: Formulas
  • 32.
  • 33.
  • 34.
  • 35.
  • 36.
  • 37.
  • 38.    1 0 1 0 0 0 0 1 1 0 1 UG-stress Grammar and Assignment rules word PLD Cue-based Learning
  • 39. Parameters (with setting for Dutch) Feet are / aren’t assigned iteratively P10 Weak foot looses / doesn’t loose foot status in a clash P9 Left / Right -most syllable is extra-metrical P8 There isn’t / is an extra-metrical syllable P8A Strong node in foot must / mustn’t branch P7 Feet are quantity-sensitive w.r.t. rime / nucleus P6 Feet are / are not quantity-sensitive P5 Feet right/ left -dominant P4 Feet assigned from the left/ right edge P3 Binary/ unbound feet P2 Word tree right /left dominant P1 Value Parameter
  • 40.
  • 41. Syllable-structure representations Retrieval or Similarity-based reasoning on exemplars word PLD Storage Stress pattern
  • 42.
  • 43. MBLP vs. Youpie 81% 176 YOUPIE-languages 41% 89 MBLP-languages 95% 11.88 YOUPIE-syllables 97% 3.7 MBLP-syllables 90% 28.24 105 YOUPIE-words 89% 15.01 104 MBLP-words Accuracy Sd Score System and level
  • 44.
  • 45.
  • 46.
  • 48.
  • 50.
  • 51.
  • 52.
  • 53.
  • 56.
  • 57.
  • 58.
  • 59. Simulation with TiMBL Demonstration: German plural
  • 60.
  • 61.
  • 62.
  • 63.
  • 64.
  • 65.
  • 66.
  • 67.
  • 68.
  • 69.
  • 70.
  • 71.  
  • 72.
  • 73.  
  • 74.
  • 75.  
  • 76.  
  • 77.
  • 78.
  • 79.
  • 80.
  • 81.