SlideShare a Scribd company logo
Word Recognition Models




           Lucas Rizoli
           Thursday, September 30
           PSYC 365*, Fall 2004
           Queen’s University, Kingston
Human Word Recognition
●   Text interpreted as it is perceived
    –   Stroop test (Red, Green, Yellow)
    –   Aware of results, not of processes
         ●   Likely involves many areas of brain
              –   Visual
              –   Semantic
              –   Phonological
              –   Articulatory
●   How can we model this?
Creating a Word Recognition Model
●   Assumptions
    –   Working in English
    –   Only monosyllabic words
         ●   FOX, CAVE, FEIGN...
    –   Concerned only with simple word recognition
         ●   Symbols → sounds
         ●   Visual, articulatory systems function independently
         ●   Context of word is irrelevant
Creating a Word Recognition Model
●   Rules by which to recognize CAVE
    –   C → /k/
    –   A → /A/
    –   VE → /v/
●   Describe grapheme-phoneme correspondences
    (GPC)
    –   Grapheme → phoneme
Creating a Word Recognition Model
●   Recognize HAVE
    –   H → /h/
    –   A → /A/
    –   VE → /v/
    –   So HAVE → /hAv/ ?
●   Rules result in incorrect pronunciation
Creating a Word Recognition Model
●   English is quasi-regular
    –   Can be described as systematic, but with exceptions
    –   English has a deep orthography
         ●   grapheme → phoneme rules inconsistent
              –   GAVE, CAVE, SHAVE end with /Av/
              –   HAVE ends with /@v/
Creating a Word Recognition Model
●   Models needs to recognize irregular words
●   Check for irregular words before applying GPCs
    –   List irregular words and their pronunciations
         ●   HAVE → /h@v/, GONE → /gon/, ...
    –   Have separate look-up process
Our Word Recognition Model
From Visual System
                            Orthographic Input




                Irregular
                                                  GPCs
                 Words




                            Phonological Output
                                                   To Articulatory System
The Dual-Route Model
●   Proposed by Max Coltheart in 1978
    –   Supported by Pinker, Besner
    –   Revised throughout the 80’s, 90’s, 00’s
         ●   Context sensitive rules
         ●   Rule frequency checks
         ●   Lots of other complex stuff
●   We’ll follow his 1993 model (DR93)
DR93 Examples




                                  Note: Above, /a/ should be /@/


Context-sensitive GPC
What’s Good About DR93
●   Regular word pronunciation
    –   Goes well with rule-based theories
         ●   Berko’s Wug test (This is a wug, these are two wug_)
         ●   Childhood over-regularization
●   Nonword pronunciation
    –   NUST, FAIJE, NARF are alright
What’s Not Good About DR93
●   Irregular word pronunciation
    –   GONE → /dOn/, ARE → /Ar/
●   GPCs miss subregularities
    –   OW → /aW/, from HOW, COW, PLOW
    –   SHOW, ROW, KNOW are exceptions
●   Biological plausibility
    –   Do humans need explicit rules in order to read?
The SM89 Model
●   Implemented by Seidenberg and
    McClelland in 1989
    –   Response to dual-route model
    –   Neural network/PDP model
    –   “As little as possible of the solution built
        in”
    –   “As much as possible is left to the
        mechanisms of learning”
●   We’ll call it SM89
The SM89 Model

                             Hidden Units
                               (200 units)




        Orthographic Units                   Phonological Units
             (400 units)                          (460 units)




From Visual System                               To Articulatory System
The SM89 Model
                     ●   Orthographic units are
                         triples
                         –   Three characters
                         –   Letters or word-border
Orthographic Units       –   CAVE
     (400 units)
                              ●   _CA, CAV, AVE, VE_
                         –   Context-sensitive
The SM89 Model

                         Hidden Units
                           (200 units)


●   Hidden units needed for complete neural network
●   Encode information in a non-specified way
●   Learning occurs by changing weights on
    connections to and from hidden units
    –   Process of back-propagation
The SM89 Model
●   Phonological units are
    also triples
    –   /kAv/
         ●   _kA, kAv, Av_
●   Triples are generalized             Phonological Units
                                             (460 units)
         ●   [stop, vowel, fricative]
●   Number of units are
    sufficient for English
    monosyllables
How SM89 Learns
●   Orthographic units artificially stimulated
●   Activation spreads to hidden, phonological units
    –   Feedforward from ortho. to phono. units
●   Model response is pattern of activation in
    phonological units
How SM89 Learns
●   Difference in activation between response and the
    correct activation

●   Error computed as the sum of difference for each
    unit, squared

●   Weights of all connections between units
    adjusted
How SM89 Learns



●   Simply, it learns to pronounce words properly
    –   Don’t worry about the equations
How SM89 Learns
●   Trained using a list of ~ 3000 English
    monosyllabic words
    –   Includes homographs (WIND, READ) and irregulars
●   Each training session called an epoch
●   Words appeared somewhat proportionately to
    their frequency in written language
Practical Limits on SM89’s Training
●   Activation calculated in a single step
    –   Impossible to record how long it took to respond
    –   Correlated error scores with latency
         ●   Error → time
●   Frequency of words was compressed
    –   Would’ve required ~ 34 times more epochs
    –   Saved computer time
How SM89 Performed
How SM89 Performed




Human            SM89
What’s Good About SM89
●   Regular word pronunciation
●   Irregular word pronunciation
●   Similar results to human studies
    –   Word naming latencies
    –   Priming effects
●   Behaviour the result of learning
    –   Ability increases in human fashion
What’s Not Good About SM89
●   Nonword pronunciation
    –   Significantly worse than skilled readers
    –   JINJE, FAIJE, TUNCE pronounced strangely
●   Design was awkward
    –   Triples
    –   Feedforward network
    –   Compressed word frequencies
    –   Single-step computation
The SM94 Model
●   Seidenberg, Plaut, and
    McClelland revise SM89 in 1994
    –   Response to criticism of SM89’s
        poor nonword performance
●   We’ll call this model SM94
●   Compared humans’ nonword
    responses with model’s responses
The SM94 Model

                           Hidden Units
                             (100 units)




         Graphemic Units                   Phonological Units
             (108 units)                        (50 units)




From Visual System                             To Articulatory System
How SM94 Differs From SM89
●   Feedback loops for hidden and phonemic units
●   Weights adjusted using cross-entropy method
    –   Complicated math, results in better learning
●   Not computed in a single step
●   No more triples
    –   Graphemes for word input
    –   Phonemes for word output
    –   Input based on syllable structure
Examples of SM94’s Units
Nonwords
●   May be similar to regular words
    –   SMURF ← TURF
●   In many cases there are many responses
    –   BREAT
        ●   ← EAT ?
        ●   ← GREAT ?
        ●   ← YEAH ?
Nonwords




  Human
How SM94 and DR93 Performed




            Note: Above, PDP is SM94; Rules is DR93
Comparing SM94 and DR93
●   Both perform well with list of ~ 3000 words
    –   SM94 responds 99.7% correctly, DR93 78%
●   Both do well with nonwords
    –   SM89’s weakness caused by design issues
         ●   SM94 avoids such issues
    –   Neural networks equally capable for nonwords
Comparing SM94 and DR93
●   SM94 is a good performer
    –   Regular, irregular words
    –   Behaviour similar to human
         ●   Latency effects
         ●   Nonword pronunciation
●   DR93 still has problems
    –   Trouble with irregular words
    –   More likely to regularize words
Models and Dyslexia
●   Consider specific types of dyslexia
    –   Phonological Dyslexia
         ●   Trouble pronouncing nonwords
    –   Surface Dyslexia
         ●   Trouble with irregular words
    –   Developmental Dyslexia
         ●   Inability to read at age-appropriate level
●   How can word recognition models account for
    dyslexic behaviour?
DR93 and Dyslexia
●   Phonological dyslexia as damage to GPC route
    –   Cannot compile sounds from graphemes
    –   Relies on look-up
●   Surface dyslexia as damage to look-up route
    –   Cannot remember irregular words
    –   Relies on GPCs
●   Developmental dyslexia
    –   Problems somewhere along either route
         ●   Cannot form GPCs, slow look-up, for example
SM89 and Dyslexia
●   Developmental dyslexia as damaged or missing
    hidden units




      200 Hidden Units            100 Hidden Units
The 1996 Models and Dyslexia
●   Plaut, McClelland, Seidenberg, and Patterson
    study networks and dyslexia (1996)
    –   Variations of the SM89/SM94 models
         ●   Feedforward
         ●   Feedforward with actual word-frequencies
         ●   Feedback with attractors
         ●   Feedback with attractors and semantic processes
    –   Compare each to case studies of dyslexics
Feedforward and Dyslexia Case-
           Studies
Feedback, with Attractors and
Semantics, and Dyslexia Case-Studies
The 1996 Models and Dyslexia
●   Most complex damage caused closest results
    –   Not as simple as removing hidden units
         ●   Severing semantics
         ●   Distorting attractors
●   Results are encouraging
Questions or Comments

More Related Content

What's hot

First and Second Language Aquisition Theories
First and Second Language Aquisition TheoriesFirst and Second Language Aquisition Theories
First and Second Language Aquisition Theories
Sheila Rad
 
Brain and Language
Brain and LanguageBrain and Language
Brain and Language
Joy Marie Dinglasa Blasco
 
Language disorders Group 3
Language disorders Group 3Language disorders Group 3
Language disorders Group 3
Umm-e-Rooman Yaqoob
 
Visual Word Recognition. The Journey from Features to Meaning
Visual Word Recognition. The Journey from Features to MeaningVisual Word Recognition. The Journey from Features to Meaning
Visual Word Recognition. The Journey from Features to Meaning
fawzia
 
Universal grammar
Universal grammarUniversal grammar
Universal grammar
Muhammad Al Fateh
 
Approaches To Language Acquisition
Approaches To Language AcquisitionApproaches To Language Acquisition
Approaches To Language Acquisition
guestb5e1f06d
 
1. models of word recognition
1. models of word recognition1. models of word recognition
1. models of word recognition
Hemaraja Nayaka S
 
The innateness theory chomsky presentation
The innateness theory  chomsky presentationThe innateness theory  chomsky presentation
The innateness theory chomsky presentation
Jess Roebuck
 
Phonlogical acquistion
Phonlogical acquistionPhonlogical acquistion
Phonlogical acquistion
Lama Albabtain
 
Bilinguals and Bilingualism
Bilinguals and BilingualismBilinguals and Bilingualism
Bilinguals and Bilingualism
Jerica Pelaez
 
language and the Brain
language and the Brainlanguage and the Brain
language and the Brain
Abdul Aziz Assanosi
 
STAGES OF LANGUAGE ACQUISITION
STAGES OF LANGUAGE ACQUISITIONSTAGES OF LANGUAGE ACQUISITION
STAGES OF LANGUAGE ACQUISITION
Ladie Ballesteros
 
Production and Comprehension Process of Language
Production and Comprehension Process of LanguageProduction and Comprehension Process of Language
Production and Comprehension Process of Language
Riska Daenangsari
 
Chapter 1 Language Learning in Early Childhood
Chapter 1 Language Learning in Early ChildhoodChapter 1 Language Learning in Early Childhood
Chapter 1 Language Learning in Early Childhood
Vin Simon
 
Second language acquisition
Second language acquisitionSecond language acquisition
Second language acquisition
kashmasardar
 
Language And Brain Development
Language And Brain DevelopmentLanguage And Brain Development
Language And Brain Development
Marilyn Amoro
 
CH 5 Social Contexts of Second Language Acquisition.pptx
CH 5 Social Contexts of Second Language Acquisition.pptxCH 5 Social Contexts of Second Language Acquisition.pptx
CH 5 Social Contexts of Second Language Acquisition.pptx
VATHVARY
 
Language Acquisition: Lecture 2 Phonological Development
Language Acquisition: Lecture 2 Phonological DevelopmentLanguage Acquisition: Lecture 2 Phonological Development
Language Acquisition: Lecture 2 Phonological Development
suascolleges
 
Language Acquisition
Language AcquisitionLanguage Acquisition
Language Acquisition
Milton Gomez
 
Language acquisition device (LAD) / Universal Grammar (UG)
Language acquisition device (LAD) / Universal Grammar (UG) Language acquisition device (LAD) / Universal Grammar (UG)
Language acquisition device (LAD) / Universal Grammar (UG)
atravesanoud
 

What's hot (20)

First and Second Language Aquisition Theories
First and Second Language Aquisition TheoriesFirst and Second Language Aquisition Theories
First and Second Language Aquisition Theories
 
Brain and Language
Brain and LanguageBrain and Language
Brain and Language
 
Language disorders Group 3
Language disorders Group 3Language disorders Group 3
Language disorders Group 3
 
Visual Word Recognition. The Journey from Features to Meaning
Visual Word Recognition. The Journey from Features to MeaningVisual Word Recognition. The Journey from Features to Meaning
Visual Word Recognition. The Journey from Features to Meaning
 
Universal grammar
Universal grammarUniversal grammar
Universal grammar
 
Approaches To Language Acquisition
Approaches To Language AcquisitionApproaches To Language Acquisition
Approaches To Language Acquisition
 
1. models of word recognition
1. models of word recognition1. models of word recognition
1. models of word recognition
 
The innateness theory chomsky presentation
The innateness theory  chomsky presentationThe innateness theory  chomsky presentation
The innateness theory chomsky presentation
 
Phonlogical acquistion
Phonlogical acquistionPhonlogical acquistion
Phonlogical acquistion
 
Bilinguals and Bilingualism
Bilinguals and BilingualismBilinguals and Bilingualism
Bilinguals and Bilingualism
 
language and the Brain
language and the Brainlanguage and the Brain
language and the Brain
 
STAGES OF LANGUAGE ACQUISITION
STAGES OF LANGUAGE ACQUISITIONSTAGES OF LANGUAGE ACQUISITION
STAGES OF LANGUAGE ACQUISITION
 
Production and Comprehension Process of Language
Production and Comprehension Process of LanguageProduction and Comprehension Process of Language
Production and Comprehension Process of Language
 
Chapter 1 Language Learning in Early Childhood
Chapter 1 Language Learning in Early ChildhoodChapter 1 Language Learning in Early Childhood
Chapter 1 Language Learning in Early Childhood
 
Second language acquisition
Second language acquisitionSecond language acquisition
Second language acquisition
 
Language And Brain Development
Language And Brain DevelopmentLanguage And Brain Development
Language And Brain Development
 
CH 5 Social Contexts of Second Language Acquisition.pptx
CH 5 Social Contexts of Second Language Acquisition.pptxCH 5 Social Contexts of Second Language Acquisition.pptx
CH 5 Social Contexts of Second Language Acquisition.pptx
 
Language Acquisition: Lecture 2 Phonological Development
Language Acquisition: Lecture 2 Phonological DevelopmentLanguage Acquisition: Lecture 2 Phonological Development
Language Acquisition: Lecture 2 Phonological Development
 
Language Acquisition
Language AcquisitionLanguage Acquisition
Language Acquisition
 
Language acquisition device (LAD) / Universal Grammar (UG)
Language acquisition device (LAD) / Universal Grammar (UG) Language acquisition device (LAD) / Universal Grammar (UG)
Language acquisition device (LAD) / Universal Grammar (UG)
 

More from Lucas Rizoli

A Multimedia Interface For Facilitating Comparisons Of Opinions (Thesis Prese...
A Multimedia Interface For Facilitating Comparisons Of Opinions (Thesis Prese...A Multimedia Interface For Facilitating Comparisons Of Opinions (Thesis Prese...
A Multimedia Interface For Facilitating Comparisons Of Opinions (Thesis Prese...
Lucas Rizoli
 
Brasilia
BrasiliaBrasilia
Brasilia
Lucas Rizoli
 
Thoughts on the use of Analogies in Understanding and Solving Complex Problem...
Thoughts on the use of Analogies in Understanding and Solving Complex Problem...Thoughts on the use of Analogies in Understanding and Solving Complex Problem...
Thoughts on the use of Analogies in Understanding and Solving Complex Problem...
Lucas Rizoli
 
World Bank
World BankWorld Bank
World Bank
Lucas Rizoli
 
Recognizing Strong and Weak Opinion Clauses
Recognizing Strong and Weak Opinion ClausesRecognizing Strong and Weak Opinion Clauses
Recognizing Strong and Weak Opinion Clauses
Lucas Rizoli
 
Modeling and Adapting to Cognitive Load
Modeling and Adapting to Cognitive LoadModeling and Adapting to Cognitive Load
Modeling and Adapting to Cognitive Load
Lucas Rizoli
 
Fitts' Law Basics
Fitts' Law BasicsFitts' Law Basics
Fitts' Law Basics
Lucas Rizoli
 
Our Victorian Now
Our Victorian NowOur Victorian Now
Our Victorian Now
Lucas Rizoli
 
On Google
On GoogleOn Google
On Google
Lucas Rizoli
 
Communication is Viral
Communication is ViralCommunication is Viral
Communication is Viral
Lucas Rizoli
 

More from Lucas Rizoli (10)

A Multimedia Interface For Facilitating Comparisons Of Opinions (Thesis Prese...
A Multimedia Interface For Facilitating Comparisons Of Opinions (Thesis Prese...A Multimedia Interface For Facilitating Comparisons Of Opinions (Thesis Prese...
A Multimedia Interface For Facilitating Comparisons Of Opinions (Thesis Prese...
 
Brasilia
BrasiliaBrasilia
Brasilia
 
Thoughts on the use of Analogies in Understanding and Solving Complex Problem...
Thoughts on the use of Analogies in Understanding and Solving Complex Problem...Thoughts on the use of Analogies in Understanding and Solving Complex Problem...
Thoughts on the use of Analogies in Understanding and Solving Complex Problem...
 
World Bank
World BankWorld Bank
World Bank
 
Recognizing Strong and Weak Opinion Clauses
Recognizing Strong and Weak Opinion ClausesRecognizing Strong and Weak Opinion Clauses
Recognizing Strong and Weak Opinion Clauses
 
Modeling and Adapting to Cognitive Load
Modeling and Adapting to Cognitive LoadModeling and Adapting to Cognitive Load
Modeling and Adapting to Cognitive Load
 
Fitts' Law Basics
Fitts' Law BasicsFitts' Law Basics
Fitts' Law Basics
 
Our Victorian Now
Our Victorian NowOur Victorian Now
Our Victorian Now
 
On Google
On GoogleOn Google
On Google
 
Communication is Viral
Communication is ViralCommunication is Viral
Communication is Viral
 

Recently uploaded

GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
Tomaz Bratanic
 
Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024
Jason Packer
 
AWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptxAWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptx
HarisZaheer8
 
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
Alex Pruden
 
Introduction of Cybersecurity with OSS at Code Europe 2024
Introduction of Cybersecurity with OSS  at Code Europe 2024Introduction of Cybersecurity with OSS  at Code Europe 2024
Introduction of Cybersecurity with OSS at Code Europe 2024
Hiroshi SHIBATA
 
SAP S/4 HANA sourcing and procurement to Public cloud
SAP S/4 HANA sourcing and procurement to Public cloudSAP S/4 HANA sourcing and procurement to Public cloud
SAP S/4 HANA sourcing and procurement to Public cloud
maazsz111
 
Dandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity serverDandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity server
Antonios Katsarakis
 
Taking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdfTaking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdf
ssuserfac0301
 
JavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green MasterplanJavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green Masterplan
Miro Wengner
 
Nordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptxNordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptx
MichaelKnudsen27
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
panagenda
 
June Patch Tuesday
June Patch TuesdayJune Patch Tuesday
June Patch Tuesday
Ivanti
 
Azure API Management to expose backend services securely
Azure API Management to expose backend services securelyAzure API Management to expose backend services securely
Azure API Management to expose backend services securely
Dinusha Kumarasiri
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
Chart Kalyan
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
DanBrown980551
 
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying AheadDigital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Wask
 
Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
Tatiana Kojar
 
GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)
Javier Junquera
 
A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024
Intelisync
 
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdfMonitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Tosin Akinosho
 

Recently uploaded (20)

GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
 
Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024
 
AWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptxAWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptx
 
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
 
Introduction of Cybersecurity with OSS at Code Europe 2024
Introduction of Cybersecurity with OSS  at Code Europe 2024Introduction of Cybersecurity with OSS  at Code Europe 2024
Introduction of Cybersecurity with OSS at Code Europe 2024
 
SAP S/4 HANA sourcing and procurement to Public cloud
SAP S/4 HANA sourcing and procurement to Public cloudSAP S/4 HANA sourcing and procurement to Public cloud
SAP S/4 HANA sourcing and procurement to Public cloud
 
Dandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity serverDandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity server
 
Taking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdfTaking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdf
 
JavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green MasterplanJavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green Masterplan
 
Nordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptxNordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptx
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
 
June Patch Tuesday
June Patch TuesdayJune Patch Tuesday
June Patch Tuesday
 
Azure API Management to expose backend services securely
Azure API Management to expose backend services securelyAzure API Management to expose backend services securely
Azure API Management to expose backend services securely
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
 
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying AheadDigital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying Ahead
 
Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
 
GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)
 
A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024
 
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdfMonitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdf
 

Word Recognition Models

  • 1. Word Recognition Models Lucas Rizoli Thursday, September 30 PSYC 365*, Fall 2004 Queen’s University, Kingston
  • 2. Human Word Recognition ● Text interpreted as it is perceived – Stroop test (Red, Green, Yellow) – Aware of results, not of processes ● Likely involves many areas of brain – Visual – Semantic – Phonological – Articulatory ● How can we model this?
  • 3. Creating a Word Recognition Model ● Assumptions – Working in English – Only monosyllabic words ● FOX, CAVE, FEIGN... – Concerned only with simple word recognition ● Symbols → sounds ● Visual, articulatory systems function independently ● Context of word is irrelevant
  • 4. Creating a Word Recognition Model ● Rules by which to recognize CAVE – C → /k/ – A → /A/ – VE → /v/ ● Describe grapheme-phoneme correspondences (GPC) – Grapheme → phoneme
  • 5. Creating a Word Recognition Model ● Recognize HAVE – H → /h/ – A → /A/ – VE → /v/ – So HAVE → /hAv/ ? ● Rules result in incorrect pronunciation
  • 6. Creating a Word Recognition Model ● English is quasi-regular – Can be described as systematic, but with exceptions – English has a deep orthography ● grapheme → phoneme rules inconsistent – GAVE, CAVE, SHAVE end with /Av/ – HAVE ends with /@v/
  • 7. Creating a Word Recognition Model ● Models needs to recognize irregular words ● Check for irregular words before applying GPCs – List irregular words and their pronunciations ● HAVE → /h@v/, GONE → /gon/, ... – Have separate look-up process
  • 8. Our Word Recognition Model From Visual System Orthographic Input Irregular GPCs Words Phonological Output To Articulatory System
  • 9. The Dual-Route Model ● Proposed by Max Coltheart in 1978 – Supported by Pinker, Besner – Revised throughout the 80’s, 90’s, 00’s ● Context sensitive rules ● Rule frequency checks ● Lots of other complex stuff ● We’ll follow his 1993 model (DR93)
  • 10. DR93 Examples Note: Above, /a/ should be /@/ Context-sensitive GPC
  • 11. What’s Good About DR93 ● Regular word pronunciation – Goes well with rule-based theories ● Berko’s Wug test (This is a wug, these are two wug_) ● Childhood over-regularization ● Nonword pronunciation – NUST, FAIJE, NARF are alright
  • 12. What’s Not Good About DR93 ● Irregular word pronunciation – GONE → /dOn/, ARE → /Ar/ ● GPCs miss subregularities – OW → /aW/, from HOW, COW, PLOW – SHOW, ROW, KNOW are exceptions ● Biological plausibility – Do humans need explicit rules in order to read?
  • 13. The SM89 Model ● Implemented by Seidenberg and McClelland in 1989 – Response to dual-route model – Neural network/PDP model – “As little as possible of the solution built in” – “As much as possible is left to the mechanisms of learning” ● We’ll call it SM89
  • 14. The SM89 Model Hidden Units (200 units) Orthographic Units Phonological Units (400 units) (460 units) From Visual System To Articulatory System
  • 15. The SM89 Model ● Orthographic units are triples – Three characters – Letters or word-border Orthographic Units – CAVE (400 units) ● _CA, CAV, AVE, VE_ – Context-sensitive
  • 16. The SM89 Model Hidden Units (200 units) ● Hidden units needed for complete neural network ● Encode information in a non-specified way ● Learning occurs by changing weights on connections to and from hidden units – Process of back-propagation
  • 17. The SM89 Model ● Phonological units are also triples – /kAv/ ● _kA, kAv, Av_ ● Triples are generalized Phonological Units (460 units) ● [stop, vowel, fricative] ● Number of units are sufficient for English monosyllables
  • 18. How SM89 Learns ● Orthographic units artificially stimulated ● Activation spreads to hidden, phonological units – Feedforward from ortho. to phono. units ● Model response is pattern of activation in phonological units
  • 19. How SM89 Learns ● Difference in activation between response and the correct activation ● Error computed as the sum of difference for each unit, squared ● Weights of all connections between units adjusted
  • 20. How SM89 Learns ● Simply, it learns to pronounce words properly – Don’t worry about the equations
  • 21. How SM89 Learns ● Trained using a list of ~ 3000 English monosyllabic words – Includes homographs (WIND, READ) and irregulars ● Each training session called an epoch ● Words appeared somewhat proportionately to their frequency in written language
  • 22. Practical Limits on SM89’s Training ● Activation calculated in a single step – Impossible to record how long it took to respond – Correlated error scores with latency ● Error → time ● Frequency of words was compressed – Would’ve required ~ 34 times more epochs – Saved computer time
  • 25. What’s Good About SM89 ● Regular word pronunciation ● Irregular word pronunciation ● Similar results to human studies – Word naming latencies – Priming effects ● Behaviour the result of learning – Ability increases in human fashion
  • 26. What’s Not Good About SM89 ● Nonword pronunciation – Significantly worse than skilled readers – JINJE, FAIJE, TUNCE pronounced strangely ● Design was awkward – Triples – Feedforward network – Compressed word frequencies – Single-step computation
  • 27. The SM94 Model ● Seidenberg, Plaut, and McClelland revise SM89 in 1994 – Response to criticism of SM89’s poor nonword performance ● We’ll call this model SM94 ● Compared humans’ nonword responses with model’s responses
  • 28. The SM94 Model Hidden Units (100 units) Graphemic Units Phonological Units (108 units) (50 units) From Visual System To Articulatory System
  • 29. How SM94 Differs From SM89 ● Feedback loops for hidden and phonemic units ● Weights adjusted using cross-entropy method – Complicated math, results in better learning ● Not computed in a single step ● No more triples – Graphemes for word input – Phonemes for word output – Input based on syllable structure
  • 31. Nonwords ● May be similar to regular words – SMURF ← TURF ● In many cases there are many responses – BREAT ● ← EAT ? ● ← GREAT ? ● ← YEAH ?
  • 33. How SM94 and DR93 Performed Note: Above, PDP is SM94; Rules is DR93
  • 34. Comparing SM94 and DR93 ● Both perform well with list of ~ 3000 words – SM94 responds 99.7% correctly, DR93 78% ● Both do well with nonwords – SM89’s weakness caused by design issues ● SM94 avoids such issues – Neural networks equally capable for nonwords
  • 35. Comparing SM94 and DR93 ● SM94 is a good performer – Regular, irregular words – Behaviour similar to human ● Latency effects ● Nonword pronunciation ● DR93 still has problems – Trouble with irregular words – More likely to regularize words
  • 36. Models and Dyslexia ● Consider specific types of dyslexia – Phonological Dyslexia ● Trouble pronouncing nonwords – Surface Dyslexia ● Trouble with irregular words – Developmental Dyslexia ● Inability to read at age-appropriate level ● How can word recognition models account for dyslexic behaviour?
  • 37. DR93 and Dyslexia ● Phonological dyslexia as damage to GPC route – Cannot compile sounds from graphemes – Relies on look-up ● Surface dyslexia as damage to look-up route – Cannot remember irregular words – Relies on GPCs ● Developmental dyslexia – Problems somewhere along either route ● Cannot form GPCs, slow look-up, for example
  • 38. SM89 and Dyslexia ● Developmental dyslexia as damaged or missing hidden units 200 Hidden Units 100 Hidden Units
  • 39. The 1996 Models and Dyslexia ● Plaut, McClelland, Seidenberg, and Patterson study networks and dyslexia (1996) – Variations of the SM89/SM94 models ● Feedforward ● Feedforward with actual word-frequencies ● Feedback with attractors ● Feedback with attractors and semantic processes – Compare each to case studies of dyslexics
  • 40. Feedforward and Dyslexia Case- Studies
  • 41. Feedback, with Attractors and Semantics, and Dyslexia Case-Studies
  • 42. The 1996 Models and Dyslexia ● Most complex damage caused closest results – Not as simple as removing hidden units ● Severing semantics ● Distorting attractors ● Results are encouraging