SlideShare a Scribd company logo
Cognitive plausibility in learning algorithms
With application to natural language processing
Arvi Tavast, PhD
Qlaara Labs, UT, TLU
Tallinn, 10 May 2016
Introduction Understanding humans Results Application
Motivation
Why cognitive plausibility?
Objective: best product vs best research
Model the brain
End-to-end learning from raw unlabelled data
Grounded cognition
Cognitive computing, neuromorphic computing
Feedback loop: using the model to better understand the
object to be modelled
Introduction Understanding humans Results Application
Outline
Heretical view on language - established learning model - application to NLP
1 Introduction
2 Understanding humans
Understanding human communication
Understanding human learning
Rescorla-Wagner learning model
3 Results
4 Application
Naive Discrimination Learning
Introduction Understanding humans Results Application
My background
mainly in linguistics
1993 TUT computer systems
1989-2004 IT translation
2000-2006 Microsoft MILS
2002 UT MA linguistics
2008 UT PhD linguistics
2015 Uni T ¨Ubingen postdoc quantitative linguistics
Introduction Understanding humans Results Application
Understanding human communication
How do we explain the observation that verbal communication sometimes works
The channel metaphor
Speaking is like sending things by train, selecting suitable
wagons (words) for each thing (thought)
Hearing is like decoding the message
⇒ meanings are properties of words
Communication as uncertainty reduction
Speaking is like sending blueprints for building things, which
the receiver will have to follow (subject to their abilities,
available materials, etc.)
⇒ meanings are properties of people
Hearing is like using hints to reduce our uncertainty about
the message
Introduction Understanding humans Results Application
Understanding human communication
When can the channel metaphor work?
Encoding of a message must contain a set of discriminable
states that is greater than or equal to the number of
discriminable states in the to-be-encoded message
or:
Encoding thoughts with words can only work if the number
of possible thoughts is smaller than or equal to the number
of possible words
This is the case only in restricted domains (weather forecasts)
Compare: reconstructing a document based on its hash sum
Introduction Understanding humans Results Application
Understanding human learning
Compositional vs discriminative
Possible ways of conceptualising biological learning
Compositional model: we start as an empty page, adding
knowledge like articles in an encyclopedia
Discriminative model: we start by perceiving a single object
(the world) and gradually learn to discriminate between its
parts
If discriminative:
Human language models can not be constant across time or
subjects
Introduction Understanding humans Results Application
The Rescorla-Wagner learning model
Language acquisition can be described as creating a statistical relationship
The Rescorla-Wagner model: how do we learn that Cj means O
if we see that Cj ⇒ O, the relationship is strengthened
less, if there are other cues
if we see that Cj ⇒ ¬O, the relationship is weakened
more, if there are other cues
(if we see that ¬Cj ⇒ O, the relationship is weakened)
Introduction Understanding humans Results Application
Feature-label-order effect
Creating the relationship between word and concept is only possible in one direction
Feature-label-order effect
If concept ⇒ word, the relationship is strengthened
If word ⇒ concept, the relationship is not strengthened
Number of objects in the world number of words in
language
Abstraction inevitably and irreversibly discards information
Recovering a meaning from a word is necessarily
underspecified
Ramscar, M., Yarlett, D., Dye, M., Denny, K., and Thorpe, K. (2010). The effects of feature-label-order and their
implications for symbolic learning. Cognitive Science, 34(6), 909–957.
Introduction Understanding humans Results Application
Aging and cognitive decline
Why do our verbal abilities seem to fail around the age of 65?
Ramscar, M., Hendrix, P., Shaoul, C., Milin, P., and Baayen, H. (2014). The myth of cognitive decline: Non-linear dynamics
of lifelong learning. Topics in Cognitive Science, 6(1), 5–42.
Introduction Understanding humans Results Application
Morphology
Implicit morphology (without morphemes)
0.1
0.378
0.116
0.576
0.531
0.4190.39
0.377
0.516
0.475
0.47
0.587
0.124
0.225
0.216
0.1630.138
0.5
0.5
#mA
ki#
#tA
tA# #mt
mtA
tAk
Aki
itA
#mi
mit
At#
mAt
#m@
@tA
m@t
#m::t
m::tA
###
Introduction Understanding humans Results Application
Naive Discrimination Learning
The R package: installation and basic usage
ndl: https://cran.r-project.org/web/packages/ndl/index.html
ndl2 (+ incremental learning): contact the authors
wm = estimateWeights(events) # Danks equilibria
wm = learnWeights(events) # incremental, ndl2 only
Introduction Understanding humans Results Application
Naive Discrimination Learning
Input data for Danks estimation: frequencies
Outcomes Cues Frequency
aadress aadress S SG N 1
aadresse aadress S PL P 1
aadressil aadress S SG AD 4
aadressile aadress S SG ALL 1
aasisid aasima V SID 1
aasta aasta S SG G 2
aasta aasta S SG N 1
aastane aastane A SG N 48
Introduction Understanding humans Results Application
Naive Discrimination Learning
Input data for incremental learning: single events
Outcomes Cues Frequency
aadress aadress S SG N 1
aadresse aadress S PL P 1
aadressil aadress S SG AD 1
aadressil aadress S SG AD 1
aadressil aadress S SG AD 1
aadressil aadress S SG AD 1
aadressile aadress S SG ALL 1
aasisid aasima V SID 1
aasta aasta S SG G 1
aasta aasta S SG G 1
aasta aasta S SG N 1
aastane aastane A SG N 1
aastane aastane A SG N 1
aastane aastane A SG N 1
...
Introduction Understanding humans Results Application
Naive Discrimination Learning
Output: weight matrix, cues x outcomes
Cues Outcomes Application
letter ngrams words reading
character features words reading
words lexomes POS tagging
lexomes letter ngrams morphological synthesis
contexts words distributional semantics
audio signal words speech recognition
words audio signal speech synthesis
Introduction Understanding humans Results Application
Naive Discrimination Learning
About the weight matrix
What we can look at:
Similarity of outcome vectors
Similarity of cue vectors
MAD (median absolute deviation) of outcome vector
Competing cues
Introduction Understanding humans Results Application
Naive Discrimination Learning
About the weight matrix
Other properties:
No dimensionality reduction (played with 200k x 100k)
Danks equations subject to R’s 232 limit (matrix
pseudoinverse)
Slow (weeks on ca 16 cores, 200G ram)
Performance less than word2vec etc, but comparable
Introduction Understanding humans Results Application
Some NLP tools
How to get started quickly with NLP
Python NLTK
EstNLTK
Gensim (incl word2vec)
DISSECT
Java GATE (also web)
Stanford NLP
Deeplearning4j (incl word2vec)
C word2vec
R NDL
Introduction Understanding humans Results Application
Language understanding
What’s missing from full language understanding
Training material
Interannotator agreement is less than perfect
Corpus is heterogenous
This is not a methodological flaw
Communicative intent and self-awareness
If cues are lexomes (=what the speaker wanted to say), the
system must want something.
Introduction Understanding humans Results Application
Thanks for listening
Contacts and recommended reading
Contact
arvi@qlaara.com
Easy reading
blog.qlaara.com
Recommended reading
Harald Baayen
www.sfs.uni-tuebingen.de/hbaayen/
Michael Ramscar
https://michaelramscar.wordpress.com/

More Related Content

What's hot

(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结
君 廖
 
Deep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsDeep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word Embeddings
Roelof Pieters
 
Word2Vec: Learning of word representations in a vector space - Di Mitri & Her...
Word2Vec: Learning of word representations in a vector space - Di Mitri & Her...Word2Vec: Learning of word representations in a vector space - Di Mitri & Her...
Word2Vec: Learning of word representations in a vector space - Di Mitri & Her...
Daniele Di Mitri
 
Nlp presentation
Nlp presentationNlp presentation
Nlp presentation
Surya Sg
 
Nlp research presentation
Nlp research presentationNlp research presentation
Nlp research presentation
Surya Sg
 
International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI) International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)
inventionjournals
 
Possible Word Representation
Possible Word RepresentationPossible Word Representation
Possible Word Representation
chauhankapil
 
Discussion summary emergentism
Discussion summary emergentismDiscussion summary emergentism
Discussion summary emergentism
lichengcheng
 
Lecture 2: From Semantics To Semantic-Oriented Applications
Lecture 2: From Semantics To Semantic-Oriented ApplicationsLecture 2: From Semantics To Semantic-Oriented Applications
Lecture 2: From Semantics To Semantic-Oriented Applications
Marina Santini
 
Improvement in Quality of Speech associated with Braille codes - A Review
Improvement in Quality of Speech associated with Braille codes - A ReviewImprovement in Quality of Speech associated with Braille codes - A Review
Improvement in Quality of Speech associated with Braille codes - A Review
inscit2006
 
AINL 2016: Nikolenko
AINL 2016: NikolenkoAINL 2016: Nikolenko
AINL 2016: Nikolenko
Lidia Pivovarova
 
Introduction to Distributional Semantics
Introduction to Distributional SemanticsIntroduction to Distributional Semantics
Introduction to Distributional SemanticsAndre Freitas
 
Lecture 2: Computational Semantics
Lecture 2: Computational SemanticsLecture 2: Computational Semantics
Lecture 2: Computational Semantics
Marina Santini
 
Anthiil Inside workshop on NLP
Anthiil Inside workshop on NLPAnthiil Inside workshop on NLP
Anthiil Inside workshop on NLP
Satyam Saxena
 
Natural Language Processing: Parsing
Natural Language Processing: ParsingNatural Language Processing: Parsing
Natural Language Processing: Parsing
Rushdi Shams
 
An Intuitive Natural Language Understanding System
An Intuitive Natural Language Understanding SystemAn Intuitive Natural Language Understanding System
An Intuitive Natural Language Understanding System
inscit2006
 
NLP Project Presentation
NLP Project PresentationNLP Project Presentation
NLP Project Presentation
Aryak Sengupta
 
Robust rule-based parsing
Robust rule-based parsingRobust rule-based parsing
Robust rule-based parsing
Estelle Delpech
 
Deep learning for nlp
Deep learning for nlpDeep learning for nlp
Deep learning for nlp
Viet-Trung TRAN
 
Embedding for fun fumarola Meetup Milano DLI luglio
Embedding for fun fumarola Meetup Milano DLI luglioEmbedding for fun fumarola Meetup Milano DLI luglio
Embedding for fun fumarola Meetup Milano DLI luglio
Deep Learning Italia
 

What's hot (20)

(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结
 
Deep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsDeep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word Embeddings
 
Word2Vec: Learning of word representations in a vector space - Di Mitri & Her...
Word2Vec: Learning of word representations in a vector space - Di Mitri & Her...Word2Vec: Learning of word representations in a vector space - Di Mitri & Her...
Word2Vec: Learning of word representations in a vector space - Di Mitri & Her...
 
Nlp presentation
Nlp presentationNlp presentation
Nlp presentation
 
Nlp research presentation
Nlp research presentationNlp research presentation
Nlp research presentation
 
International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI) International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)
 
Possible Word Representation
Possible Word RepresentationPossible Word Representation
Possible Word Representation
 
Discussion summary emergentism
Discussion summary emergentismDiscussion summary emergentism
Discussion summary emergentism
 
Lecture 2: From Semantics To Semantic-Oriented Applications
Lecture 2: From Semantics To Semantic-Oriented ApplicationsLecture 2: From Semantics To Semantic-Oriented Applications
Lecture 2: From Semantics To Semantic-Oriented Applications
 
Improvement in Quality of Speech associated with Braille codes - A Review
Improvement in Quality of Speech associated with Braille codes - A ReviewImprovement in Quality of Speech associated with Braille codes - A Review
Improvement in Quality of Speech associated with Braille codes - A Review
 
AINL 2016: Nikolenko
AINL 2016: NikolenkoAINL 2016: Nikolenko
AINL 2016: Nikolenko
 
Introduction to Distributional Semantics
Introduction to Distributional SemanticsIntroduction to Distributional Semantics
Introduction to Distributional Semantics
 
Lecture 2: Computational Semantics
Lecture 2: Computational SemanticsLecture 2: Computational Semantics
Lecture 2: Computational Semantics
 
Anthiil Inside workshop on NLP
Anthiil Inside workshop on NLPAnthiil Inside workshop on NLP
Anthiil Inside workshop on NLP
 
Natural Language Processing: Parsing
Natural Language Processing: ParsingNatural Language Processing: Parsing
Natural Language Processing: Parsing
 
An Intuitive Natural Language Understanding System
An Intuitive Natural Language Understanding SystemAn Intuitive Natural Language Understanding System
An Intuitive Natural Language Understanding System
 
NLP Project Presentation
NLP Project PresentationNLP Project Presentation
NLP Project Presentation
 
Robust rule-based parsing
Robust rule-based parsingRobust rule-based parsing
Robust rule-based parsing
 
Deep learning for nlp
Deep learning for nlpDeep learning for nlp
Deep learning for nlp
 
Embedding for fun fumarola Meetup Milano DLI luglio
Embedding for fun fumarola Meetup Milano DLI luglioEmbedding for fun fumarola Meetup Milano DLI luglio
Embedding for fun fumarola Meetup Milano DLI luglio
 

Viewers also liked

QuickBooks to SugarCRM Integration as a SaaS Service | SugarCon 2011
QuickBooks to SugarCRM Integration as a SaaS Service | SugarCon 2011QuickBooks to SugarCRM Integration as a SaaS Service | SugarCon 2011
QuickBooks to SugarCRM Integration as a SaaS Service | SugarCon 2011
SugarCRM
 
AI Control
AI ControlAI Control
Oauth et open id connect (oidc)
Oauth et open id connect (oidc)Oauth et open id connect (oidc)
Oauth et open id connect (oidc)
Pascal Flamand
 
Lingvist - Statistical Methods in Language Learning
Lingvist - Statistical Methods in Language LearningLingvist - Statistical Methods in Language Learning
Lingvist - Statistical Methods in Language Learning
André Karpištšenko
 
Deep learning
Deep learningDeep learning
Deep learning
André Karpištšenko
 
Knowledge Discovery
Knowledge DiscoveryKnowledge Discovery
Knowledge Discovery
André Karpištšenko
 
Knowledge Discovery in Production
Knowledge Discovery in ProductionKnowledge Discovery in Production
Knowledge Discovery in Production
André Karpištšenko
 
Starship, Building Intelligent Delivery Robots
Starship, Building Intelligent Delivery RobotsStarship, Building Intelligent Delivery Robots
Starship, Building Intelligent Delivery Robots
André Karpištšenko
 
Data science for everyone
Data science for everyoneData science for everyone
Data science for everyone
André Karpištšenko
 
Machine learning in action at Pipedrive
Machine learning in action at PipedriveMachine learning in action at Pipedrive
Machine learning in action at Pipedrive
André Karpištšenko
 
alphablues - ML applied to text and image in chat bots
alphablues - ML applied to text and image in chat botsalphablues - ML applied to text and image in chat bots
alphablues - ML applied to text and image in chat bots
André Karpištšenko
 
How to Build Your Own Physical Pentesting Go-bag
How to Build Your Own Physical Pentesting Go-bagHow to Build Your Own Physical Pentesting Go-bag
How to Build Your Own Physical Pentesting Go-bag
Beau Bullock
 

Viewers also liked (12)

QuickBooks to SugarCRM Integration as a SaaS Service | SugarCon 2011
QuickBooks to SugarCRM Integration as a SaaS Service | SugarCon 2011QuickBooks to SugarCRM Integration as a SaaS Service | SugarCon 2011
QuickBooks to SugarCRM Integration as a SaaS Service | SugarCon 2011
 
AI Control
AI ControlAI Control
AI Control
 
Oauth et open id connect (oidc)
Oauth et open id connect (oidc)Oauth et open id connect (oidc)
Oauth et open id connect (oidc)
 
Lingvist - Statistical Methods in Language Learning
Lingvist - Statistical Methods in Language LearningLingvist - Statistical Methods in Language Learning
Lingvist - Statistical Methods in Language Learning
 
Deep learning
Deep learningDeep learning
Deep learning
 
Knowledge Discovery
Knowledge DiscoveryKnowledge Discovery
Knowledge Discovery
 
Knowledge Discovery in Production
Knowledge Discovery in ProductionKnowledge Discovery in Production
Knowledge Discovery in Production
 
Starship, Building Intelligent Delivery Robots
Starship, Building Intelligent Delivery RobotsStarship, Building Intelligent Delivery Robots
Starship, Building Intelligent Delivery Robots
 
Data science for everyone
Data science for everyoneData science for everyone
Data science for everyone
 
Machine learning in action at Pipedrive
Machine learning in action at PipedriveMachine learning in action at Pipedrive
Machine learning in action at Pipedrive
 
alphablues - ML applied to text and image in chat bots
alphablues - ML applied to text and image in chat botsalphablues - ML applied to text and image in chat bots
alphablues - ML applied to text and image in chat bots
 
How to Build Your Own Physical Pentesting Go-bag
How to Build Your Own Physical Pentesting Go-bagHow to Build Your Own Physical Pentesting Go-bag
How to Build Your Own Physical Pentesting Go-bag
 

Similar to Cognitive plausibility in learning algorithms

REPORT.doc
REPORT.docREPORT.doc
dialogue act modeling for automatic tagging and recognition
 dialogue act modeling for automatic tagging and recognition dialogue act modeling for automatic tagging and recognition
dialogue act modeling for automatic tagging and recognition
Vipul Munot
 
The Geometry of Learning
The Geometry of LearningThe Geometry of Learning
The Geometry of Learning
fridolin.wild
 
Chunker Based Sentiment Analysis and Tense Classification for Nepali Text
Chunker Based Sentiment Analysis and Tense Classification for Nepali TextChunker Based Sentiment Analysis and Tense Classification for Nepali Text
Chunker Based Sentiment Analysis and Tense Classification for Nepali Text
kevig
 
Chunker Based Sentiment Analysis and Tense Classification for Nepali Text
Chunker Based Sentiment Analysis and Tense Classification for Nepali TextChunker Based Sentiment Analysis and Tense Classification for Nepali Text
Chunker Based Sentiment Analysis and Tense Classification for Nepali Text
kevig
 
NLP introduced and in 47 slides Lecture 1.ppt
NLP introduced and in 47 slides Lecture 1.pptNLP introduced and in 47 slides Lecture 1.ppt
NLP introduced and in 47 slides Lecture 1.ppt
OlusolaTop
 
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIESTHE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
kevig
 
Multi-modal NLP Systems in Healthcare
Multi-modal NLP Systems in HealthcareMulti-modal NLP Systems in Healthcare
Multi-modal NLP Systems in Healthcare
Jekaterina Novikova, PhD
 
2-Chapter Two-N-gram Language Models.ppt
2-Chapter Two-N-gram Language Models.ppt2-Chapter Two-N-gram Language Models.ppt
2-Chapter Two-N-gram Language Models.ppt
milkesa13
 
Self-Regulated Learning Nudges
Self-Regulated Learning NudgesSelf-Regulated Learning Nudges
Self-Regulated Learning Nudges
Milos Kravcik
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
punedevscom
 
A neural probabilistic language model
A neural probabilistic language modelA neural probabilistic language model
A neural probabilistic language model
c sharada
 
Challenges in transfer learning in nlp
Challenges in transfer learning in nlpChallenges in transfer learning in nlp
Challenges in transfer learning in nlp
LaraOlmosCamarena
 
Neural word embedding and language modelling
Neural word embedding and language modellingNeural word embedding and language modelling
Neural word embedding and language modelling
Riddhi Jain
 
AINL 2016: Eyecioglu
AINL 2016: EyeciogluAINL 2016: Eyecioglu
AINL 2016: Eyecioglu
Lidia Pivovarova
 
Suggestion Generation for Specific Erroneous Part in a Sentence using Deep Le...
Suggestion Generation for Specific Erroneous Part in a Sentence using Deep Le...Suggestion Generation for Specific Erroneous Part in a Sentence using Deep Le...
Suggestion Generation for Specific Erroneous Part in a Sentence using Deep Le...
ijtsrd
 
Natural language procssing
Natural language procssing Natural language procssing
Natural language procssing
Rajnish Raj
 
The role of linguistic information for shallow language processing
The role of linguistic information for shallow language processingThe role of linguistic information for shallow language processing
The role of linguistic information for shallow language processing
Constantin Orasan
 

Similar to Cognitive plausibility in learning algorithms (20)

REPORT.doc
REPORT.docREPORT.doc
REPORT.doc
 
dialogue act modeling for automatic tagging and recognition
 dialogue act modeling for automatic tagging and recognition dialogue act modeling for automatic tagging and recognition
dialogue act modeling for automatic tagging and recognition
 
The Geometry of Learning
The Geometry of LearningThe Geometry of Learning
The Geometry of Learning
 
Chunker Based Sentiment Analysis and Tense Classification for Nepali Text
Chunker Based Sentiment Analysis and Tense Classification for Nepali TextChunker Based Sentiment Analysis and Tense Classification for Nepali Text
Chunker Based Sentiment Analysis and Tense Classification for Nepali Text
 
Chunker Based Sentiment Analysis and Tense Classification for Nepali Text
Chunker Based Sentiment Analysis and Tense Classification for Nepali TextChunker Based Sentiment Analysis and Tense Classification for Nepali Text
Chunker Based Sentiment Analysis and Tense Classification for Nepali Text
 
NLP introduced and in 47 slides Lecture 1.ppt
NLP introduced and in 47 slides Lecture 1.pptNLP introduced and in 47 slides Lecture 1.ppt
NLP introduced and in 47 slides Lecture 1.ppt
 
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIESTHE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
THE ABILITY OF WORD EMBEDDINGS TO CAPTURE WORD SIMILARITIES
 
Multi-modal NLP Systems in Healthcare
Multi-modal NLP Systems in HealthcareMulti-modal NLP Systems in Healthcare
Multi-modal NLP Systems in Healthcare
 
2-Chapter Two-N-gram Language Models.ppt
2-Chapter Two-N-gram Language Models.ppt2-Chapter Two-N-gram Language Models.ppt
2-Chapter Two-N-gram Language Models.ppt
 
NLPinAAC
NLPinAACNLPinAAC
NLPinAAC
 
Self-Regulated Learning Nudges
Self-Regulated Learning NudgesSelf-Regulated Learning Nudges
Self-Regulated Learning Nudges
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
 
A neural probabilistic language model
A neural probabilistic language modelA neural probabilistic language model
A neural probabilistic language model
 
Challenges in transfer learning in nlp
Challenges in transfer learning in nlpChallenges in transfer learning in nlp
Challenges in transfer learning in nlp
 
Neural word embedding and language modelling
Neural word embedding and language modellingNeural word embedding and language modelling
Neural word embedding and language modelling
 
NLP
NLPNLP
NLP
 
AINL 2016: Eyecioglu
AINL 2016: EyeciogluAINL 2016: Eyecioglu
AINL 2016: Eyecioglu
 
Suggestion Generation for Specific Erroneous Part in a Sentence using Deep Le...
Suggestion Generation for Specific Erroneous Part in a Sentence using Deep Le...Suggestion Generation for Specific Erroneous Part in a Sentence using Deep Le...
Suggestion Generation for Specific Erroneous Part in a Sentence using Deep Le...
 
Natural language procssing
Natural language procssing Natural language procssing
Natural language procssing
 
The role of linguistic information for shallow language processing
The role of linguistic information for shallow language processingThe role of linguistic information for shallow language processing
The role of linguistic information for shallow language processing
 

Recently uploaded

SOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape ReportSOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape Report
SOCRadar
 
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
nscud
 
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Subhajit Sahu
 
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
axoqas
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP
 
Opendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptxOpendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptx
Opendatabay
 
Tabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflowsTabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflows
alex933524
 
Q1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year ReboundQ1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year Rebound
Oppotus
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
Subhajit Sahu
 
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdfSample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Linda486226
 
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
nscud
 
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
Tiktokethiodaily
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单
ewymefz
 
一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单
ewymefz
 
FP Growth Algorithm and its Applications
FP Growth Algorithm and its ApplicationsFP Growth Algorithm and its Applications
FP Growth Algorithm and its Applications
MaleehaSheikh2
 
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
ukgaet
 
tapal brand analysis PPT slide for comptetive data
tapal brand analysis PPT slide for comptetive datatapal brand analysis PPT slide for comptetive data
tapal brand analysis PPT slide for comptetive data
theahmadsaood
 
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
AbhimanyuSinha9
 
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
yhkoc
 
Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)
TravisMalana
 

Recently uploaded (20)

SOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape ReportSOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape Report
 
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
 
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
 
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
 
Opendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptxOpendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptx
 
Tabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflowsTabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflows
 
Q1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year ReboundQ1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year Rebound
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
 
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdfSample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
 
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
 
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单
 
一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单
 
FP Growth Algorithm and its Applications
FP Growth Algorithm and its ApplicationsFP Growth Algorithm and its Applications
FP Growth Algorithm and its Applications
 
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
 
tapal brand analysis PPT slide for comptetive data
tapal brand analysis PPT slide for comptetive datatapal brand analysis PPT slide for comptetive data
tapal brand analysis PPT slide for comptetive data
 
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...Best best suvichar in gujarati english meaning of this sentence as Silk road ...
Best best suvichar in gujarati english meaning of this sentence as Silk road ...
 
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
 
Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)
 

Cognitive plausibility in learning algorithms

  • 1. Cognitive plausibility in learning algorithms With application to natural language processing Arvi Tavast, PhD Qlaara Labs, UT, TLU Tallinn, 10 May 2016
  • 2. Introduction Understanding humans Results Application Motivation Why cognitive plausibility? Objective: best product vs best research Model the brain End-to-end learning from raw unlabelled data Grounded cognition Cognitive computing, neuromorphic computing Feedback loop: using the model to better understand the object to be modelled
  • 3. Introduction Understanding humans Results Application Outline Heretical view on language - established learning model - application to NLP 1 Introduction 2 Understanding humans Understanding human communication Understanding human learning Rescorla-Wagner learning model 3 Results 4 Application Naive Discrimination Learning
  • 4. Introduction Understanding humans Results Application My background mainly in linguistics 1993 TUT computer systems 1989-2004 IT translation 2000-2006 Microsoft MILS 2002 UT MA linguistics 2008 UT PhD linguistics 2015 Uni T ¨Ubingen postdoc quantitative linguistics
  • 5. Introduction Understanding humans Results Application Understanding human communication How do we explain the observation that verbal communication sometimes works The channel metaphor Speaking is like sending things by train, selecting suitable wagons (words) for each thing (thought) Hearing is like decoding the message ⇒ meanings are properties of words Communication as uncertainty reduction Speaking is like sending blueprints for building things, which the receiver will have to follow (subject to their abilities, available materials, etc.) ⇒ meanings are properties of people Hearing is like using hints to reduce our uncertainty about the message
  • 6. Introduction Understanding humans Results Application Understanding human communication When can the channel metaphor work? Encoding of a message must contain a set of discriminable states that is greater than or equal to the number of discriminable states in the to-be-encoded message or: Encoding thoughts with words can only work if the number of possible thoughts is smaller than or equal to the number of possible words This is the case only in restricted domains (weather forecasts) Compare: reconstructing a document based on its hash sum
  • 7. Introduction Understanding humans Results Application Understanding human learning Compositional vs discriminative Possible ways of conceptualising biological learning Compositional model: we start as an empty page, adding knowledge like articles in an encyclopedia Discriminative model: we start by perceiving a single object (the world) and gradually learn to discriminate between its parts If discriminative: Human language models can not be constant across time or subjects
  • 8. Introduction Understanding humans Results Application The Rescorla-Wagner learning model Language acquisition can be described as creating a statistical relationship The Rescorla-Wagner model: how do we learn that Cj means O if we see that Cj ⇒ O, the relationship is strengthened less, if there are other cues if we see that Cj ⇒ ¬O, the relationship is weakened more, if there are other cues (if we see that ¬Cj ⇒ O, the relationship is weakened)
  • 9. Introduction Understanding humans Results Application Feature-label-order effect Creating the relationship between word and concept is only possible in one direction Feature-label-order effect If concept ⇒ word, the relationship is strengthened If word ⇒ concept, the relationship is not strengthened Number of objects in the world number of words in language Abstraction inevitably and irreversibly discards information Recovering a meaning from a word is necessarily underspecified Ramscar, M., Yarlett, D., Dye, M., Denny, K., and Thorpe, K. (2010). The effects of feature-label-order and their implications for symbolic learning. Cognitive Science, 34(6), 909–957.
  • 10. Introduction Understanding humans Results Application Aging and cognitive decline Why do our verbal abilities seem to fail around the age of 65? Ramscar, M., Hendrix, P., Shaoul, C., Milin, P., and Baayen, H. (2014). The myth of cognitive decline: Non-linear dynamics of lifelong learning. Topics in Cognitive Science, 6(1), 5–42.
  • 11. Introduction Understanding humans Results Application Morphology Implicit morphology (without morphemes) 0.1 0.378 0.116 0.576 0.531 0.4190.39 0.377 0.516 0.475 0.47 0.587 0.124 0.225 0.216 0.1630.138 0.5 0.5 #mA ki# #tA tA# #mt mtA tAk Aki itA #mi mit At# mAt #m@ @tA m@t #m::t m::tA ###
  • 12. Introduction Understanding humans Results Application Naive Discrimination Learning The R package: installation and basic usage ndl: https://cran.r-project.org/web/packages/ndl/index.html ndl2 (+ incremental learning): contact the authors wm = estimateWeights(events) # Danks equilibria wm = learnWeights(events) # incremental, ndl2 only
  • 13. Introduction Understanding humans Results Application Naive Discrimination Learning Input data for Danks estimation: frequencies Outcomes Cues Frequency aadress aadress S SG N 1 aadresse aadress S PL P 1 aadressil aadress S SG AD 4 aadressile aadress S SG ALL 1 aasisid aasima V SID 1 aasta aasta S SG G 2 aasta aasta S SG N 1 aastane aastane A SG N 48
  • 14. Introduction Understanding humans Results Application Naive Discrimination Learning Input data for incremental learning: single events Outcomes Cues Frequency aadress aadress S SG N 1 aadresse aadress S PL P 1 aadressil aadress S SG AD 1 aadressil aadress S SG AD 1 aadressil aadress S SG AD 1 aadressil aadress S SG AD 1 aadressile aadress S SG ALL 1 aasisid aasima V SID 1 aasta aasta S SG G 1 aasta aasta S SG G 1 aasta aasta S SG N 1 aastane aastane A SG N 1 aastane aastane A SG N 1 aastane aastane A SG N 1 ...
  • 15. Introduction Understanding humans Results Application Naive Discrimination Learning Output: weight matrix, cues x outcomes Cues Outcomes Application letter ngrams words reading character features words reading words lexomes POS tagging lexomes letter ngrams morphological synthesis contexts words distributional semantics audio signal words speech recognition words audio signal speech synthesis
  • 16. Introduction Understanding humans Results Application Naive Discrimination Learning About the weight matrix What we can look at: Similarity of outcome vectors Similarity of cue vectors MAD (median absolute deviation) of outcome vector Competing cues
  • 17. Introduction Understanding humans Results Application Naive Discrimination Learning About the weight matrix Other properties: No dimensionality reduction (played with 200k x 100k) Danks equations subject to R’s 232 limit (matrix pseudoinverse) Slow (weeks on ca 16 cores, 200G ram) Performance less than word2vec etc, but comparable
  • 18. Introduction Understanding humans Results Application Some NLP tools How to get started quickly with NLP Python NLTK EstNLTK Gensim (incl word2vec) DISSECT Java GATE (also web) Stanford NLP Deeplearning4j (incl word2vec) C word2vec R NDL
  • 19. Introduction Understanding humans Results Application Language understanding What’s missing from full language understanding Training material Interannotator agreement is less than perfect Corpus is heterogenous This is not a methodological flaw Communicative intent and self-awareness If cues are lexomes (=what the speaker wanted to say), the system must want something.
  • 20. Introduction Understanding humans Results Application Thanks for listening Contacts and recommended reading Contact arvi@qlaara.com Easy reading blog.qlaara.com Recommended reading Harald Baayen www.sfs.uni-tuebingen.de/hbaayen/ Michael Ramscar https://michaelramscar.wordpress.com/