SlideShare a Scribd company logo
Groupings (Associations) Generation
Natural Language Processing
Andrew Ferlitsch
Quisse.Com
Problem
• Develop a method to automate the generation of Associations (Groupings).
• Used to teach associations between objects to pre-school and early school children.
• Ex.
• What item does not belong? Cat, Dog, Fire Truck, Bird
Premise
At a young age, we train children initially through rote memorization via trial and error
and correction by the adult. When we advance to associations, we are developing their
ability to learn from abstraction; that is, how do items relate to each other.
In this process, we are use the method of categorical separation. We start with categories
that are far apart; thus a child will recognize that a car (category = transportation) is too
distant from cat, dog, hamster (category = animal) without yet recognizing the finer
relationship of the grouping being household pets.
As they succeed at recognizing this coarse level of categorical separation, we narrow the
categorical hierarchy to learn how within a category the items are related, to learn less coarse
relationships.
Categorical Dictionary - Category
{ noun: ‘cat’, category: ‘Animal’ },
{ noun: ‘dog’, category: ‘Animal’},
{ noun: ‘pig’, category: ‘Animal’},
{ noun: ‘hamster’, category: ‘Animal’},
{ noun: ‘car’, category: ‘Transportation’},
{ noun: ‘airplane’, category: ‘Transportation’},
{ noun: ‘firetruck’, category: ‘Transportation’}
A categorical dictionary consists of three levels. Each entry (e.g., noun) is first
differentiated with a top-level category. For example, a noun being either an
Animal or Transportation.
Categorical Dictionary - Major
{ noun: ‘cat’, category: ‘Animal’, major: ‘Mammal’ },
{ noun: ‘dog’, category: ‘Animal’, major: ‘Mammal’},
{ noun: ‘pig’, category: ‘Animal’, major: ‘Mammal’},
{ noun: ‘tiger’, category: ‘Animal’, major: ‘Mammal’},
{ noun: ‘hamster’, category: ‘Animal’, major: ‘Mammal’},
{ noun: ‘penguin’, category: ‘Animal’, major: ‘Bird’},
{ noun: ‘snake’, category: ‘Animal’, major: ‘Reptile’},
{ noun: ‘car’, category: ‘Transportation’, major: ‘Land’},
{ noun: ‘firetruck’, category: ‘Transportation’, major: ‘Land’},
{ noun: ‘airplane’, category: ‘Transportation’, major: ‘Air’},
{ noun: ‘boat’, category: ‘Transportation’, major: ‘Water’},
For each entry in the categorical dictionary, a second property (‘major’) was added
for the next categorical level to form a two-tier hierarchy. For example, for Animal,
we have a major subcategory of mammal, fish, bird, reptile, and amphibian.
Categorical Dictionary - Minor
{ noun: ‘cat’, category: ‘Animal’, major: ‘Mammal’, minor: ‘Pet’ },
{ noun: ‘dog’, category: ‘Animal’, major: ‘Mammal’, minor: ‘Pet’},
{ noun: ‘pig’, category: ‘Animal’, major: ‘Mammal’, minor: ‘Farm’},
{ noun: ‘tiger’, category: ‘Animal’, major: ‘Mammal’, minor: ‘Wild’},
{ noun: ‘hamster’, category: ‘Animal’, major: ‘Mammal’, minor: ‘Pet’},
{ noun: ‘penguin’, category: ‘Animal’, major: ‘Bird’, minor: ‘Wild’},
For each entry in the categorical dictionary, a third property (‘minor’) was added
for the next categorical level to form a three-tier hierarchy. For example, for
Animal->Mammal, we have a minor subcategory of wild, farm and pet.
Categorical Dictionary - Blanks
{ noun: ‘animal’, category: ‘Animal’, major: ‘’, minor: ‘’ },
{ noun: ‘bird’, category: ‘Animal’, major: ‘Bird’, minor: ‘’ },
No Distinction
No Distinction
For some nouns, like bird, there is no distinction beyond the category or
major subcategory level. In this case, the next level is left blank.
Categorical Dictionary – Multiple
Entries
For other nouns, they can belong to multiple minor subcategories. For example
penguins can be both wild and flightless. In this case, the minor subcategory is a list.
{ noun: ‘penguin’, category: ‘Animal’, major: ‘Bird’, minor: [ ‘Wild’, ‘Flightless’ ] },
Association Dictionary
{ group: ‘Flightless Birds’, category: ‘Animal’, major: ‘Bird’, minor: ‘Flightless’ },
{ group: ‘Birds of Prey’, category: ‘Animal’, major: ‘Bird’, minor: ‘Predator’ }.
{ group: ‘Farm Animals’, category: ‘Animal’, major: [ ‘Mammal’, ‘Bird’], minor: ‘Farm’ }
The construction of the dictionary is similar to that of the categorical dictionary.
The group property holds a text string that is the primary key and a description of
the association. For each association, the property values for category, major and
minor are used to search for entries in the categorical dictionary that would be in
the association.
Quiz Generation
{ group: ‘Flightless Birds’, category: ‘Animal’, major: ‘Bird’, minor: ‘Flightless’ } =>
{ noun: ‘hawk’, category: ‘Animal’, major: ‘Bird’, minor: [ ‘Wild’, ‘Predator’ ] },
{ noun: ‘falcon’, category: ‘Animal’, major: ‘Bird’, minor: [ ‘Wild’, ‘Predator’ ] },
…
For each association selected (e.g., Birds of Prey), the category, and major/ minor
subcategories of the association is applied to the categorical dictionary for a matching
list of nouns
Quiz Generation
From the matching list, three nouns are selected by random (e.g., Hawk, Condor, Eagle}.
A question is then formed of the following format:
Which of the following does not belong? <noun1>, <noun2>, <noun3>, <noun4>
An answer is then formed of the following format, where description is the description
of the association (e.g., Birds of Prey).
A <noun-not> does not belong to the group <description>
Level 1 Difficulty
At the first level of difficulty, the category of the association (e.g., Animal) is used to
search the categorical dictionary for all entries not matching the category. From the
resultant matching list, one entry is chosen at random.
{ group: ‘Flightless Birds’, category: ‘Animal’, major: ‘Bird’, minor: ‘Flightless’ } =>
{ noun: ‘car’, category: ‘Transportation’},
{ noun: ‘firetruck’, category: ‘Transportation’}
…
From the matching list, one noun is randomly selected. The noun is then inserted into
the remaining placeholder of the question and <noun-not> placeholder of the answer.
Which of the following does not belong? falcon, hawk, firetruck, eagle
A firetruck does not belong to the group Birds of Prey.
Level 2 Difficulty
At the second level of difficulty, the category and the major subcategory of the
association (e.g., Animal->Bird) are used to search the categorical dictionary for all
entries that match the category, but do not match the major.
{ group: ‘Flightless Birds’, category: ‘Animal’, major: ‘Bird’, minor: ‘Flightless’ } =>
{ noun: ‘tiger’, category: ‘Animal’, major: ‘Mammal’},
{ noun: ‘pig’, category: ‘Animal’, major: ‘Mammal’}
…
From the matching list, one noun is randomly selected (e.g., tiger).
Which of the following does not belong? falcon, tiger, hawk, eagle
A tiger does not belong to the group Birds of Prey.
Level 3 Difficulty
At the third level of difficulty, the category and the major/minor subcategories of the
association (e.g., Animal->Bird->Predator) are used to search the categorical dictionary
for all entries that match the category and major subcategory, but do not match the
minor subcategory.
{ group: ‘Flightless Birds’, category: ‘Animal’, major: ‘Bird’, minor: ‘Flightless’ } =>
{ noun: ‘parrot’, category: ‘Animal’, major: ‘Bird’, minor: ‘Pet’},
{ noun: ‘cockatoo’, category: ‘Animal’, major: ‘Bird’, minor: ‘Pet’}
…
From the matching list, one noun is randomly selected (e.g., tiger).
Which of the following does not belong? falcon, eagle, cockatoo, hawk
A cockatoo does not belong to the group Birds of Prey.

More Related Content

PPT
Cog5 lecppt chapter08
PPT
Representation of knowledge
PPT
Semantic Memory_2014(1)-3.ppt
PPTX
Latent dirichlet allocation_and_topic_modeling
DOCX
Chapter 8 Thought andLanguage8.1 The Organization of
PPT
Sp616 adult lexical processing for students
PPTX
Knowledge representation
PDF
Data mining knowledge representation Notes
Cog5 lecppt chapter08
Representation of knowledge
Semantic Memory_2014(1)-3.ppt
Latent dirichlet allocation_and_topic_modeling
Chapter 8 Thought andLanguage8.1 The Organization of
Sp616 adult lexical processing for students
Knowledge representation
Data mining knowledge representation Notes

Similar to Natural Language Processing - Groupings (Associations) Generation (8)

PPTX
Representation and organization of knowledge in memory
PDF
Constructing Conceptual Knowledge Artefacts: 
 Activity Patterns in the Ontol...
PPT
Unit_II_Knowledge_Representation.ppt
PPTX
Children’s overextension of basic level vocabulary
PPT
PDF
LEARNING CONTEXT FOR TEXT.pdf
PPT
semantic.ppt
PPTX
Managing Data: storage, decisions and classification
Representation and organization of knowledge in memory
Constructing Conceptual Knowledge Artefacts: 
 Activity Patterns in the Ontol...
Unit_II_Knowledge_Representation.ppt
Children’s overextension of basic level vocabulary
LEARNING CONTEXT FOR TEXT.pdf
semantic.ppt
Managing Data: storage, decisions and classification
Ad

More from Andrew Ferlitsch (20)

PPTX
AI - Intelligent Agents
PPTX
Pareto Principle Applied to QA
PPTX
Whiteboarding Coding Challenges in Python
PPTX
Object Oriented Programming Principles
PPTX
Python - OOP Programming
PPTX
Python - Installing and Using Python and Jupyter Notepad
PPTX
Natural Language Provessing - Handling Narrarive Fields in Datasets for Class...
PPTX
Machine Learning - Introduction to Recurrent Neural Networks
PPTX
Machine Learning - Introduction to Convolutional Neural Networks
PPTX
Machine Learning - Introduction to Neural Networks
PPTX
Python - Numpy/Pandas/Matplot Machine Learning Libraries
PPTX
Machine Learning - Accuracy and Confusion Matrix
PPTX
Machine Learning - Ensemble Methods
PPTX
ML - Multiple Linear Regression
PPTX
ML - Simple Linear Regression
PPTX
Machine Learning - Dummy Variable Conversion
PPTX
Machine Learning - Splitting Datasets
PPTX
Machine Learning - Dataset Preparation
PPTX
Machine Learning - Introduction to Tensorflow
PPTX
Introduction to Machine Learning
AI - Intelligent Agents
Pareto Principle Applied to QA
Whiteboarding Coding Challenges in Python
Object Oriented Programming Principles
Python - OOP Programming
Python - Installing and Using Python and Jupyter Notepad
Natural Language Provessing - Handling Narrarive Fields in Datasets for Class...
Machine Learning - Introduction to Recurrent Neural Networks
Machine Learning - Introduction to Convolutional Neural Networks
Machine Learning - Introduction to Neural Networks
Python - Numpy/Pandas/Matplot Machine Learning Libraries
Machine Learning - Accuracy and Confusion Matrix
Machine Learning - Ensemble Methods
ML - Multiple Linear Regression
ML - Simple Linear Regression
Machine Learning - Dummy Variable Conversion
Machine Learning - Splitting Datasets
Machine Learning - Dataset Preparation
Machine Learning - Introduction to Tensorflow
Introduction to Machine Learning
Ad

Recently uploaded (20)

PDF
Architecting across the Boundaries of two Complex Domains - Healthcare & Tech...
PDF
MIND Revenue Release Quarter 2 2025 Press Release
PDF
Dropbox Q2 2025 Financial Results & Investor Presentation
PDF
Chapter 3 Spatial Domain Image Processing.pdf
PDF
Encapsulation theory and applications.pdf
PDF
The Rise and Fall of 3GPP – Time for a Sabbatical?
DOCX
The AUB Centre for AI in Media Proposal.docx
PPTX
Spectroscopy.pptx food analysis technology
PDF
Network Security Unit 5.pdf for BCA BBA.
PPTX
Understanding_Digital_Forensics_Presentation.pptx
PDF
Spectral efficient network and resource selection model in 5G networks
PDF
How UI/UX Design Impacts User Retention in Mobile Apps.pdf
PDF
Build a system with the filesystem maintained by OSTree @ COSCUP 2025
PDF
Mobile App Security Testing_ A Comprehensive Guide.pdf
PDF
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
PDF
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
PPTX
sap open course for s4hana steps from ECC to s4
PDF
Machine learning based COVID-19 study performance prediction
PPTX
ACSFv1EN-58255 AWS Academy Cloud Security Foundations.pptx
PDF
NewMind AI Weekly Chronicles - August'25 Week I
Architecting across the Boundaries of two Complex Domains - Healthcare & Tech...
MIND Revenue Release Quarter 2 2025 Press Release
Dropbox Q2 2025 Financial Results & Investor Presentation
Chapter 3 Spatial Domain Image Processing.pdf
Encapsulation theory and applications.pdf
The Rise and Fall of 3GPP – Time for a Sabbatical?
The AUB Centre for AI in Media Proposal.docx
Spectroscopy.pptx food analysis technology
Network Security Unit 5.pdf for BCA BBA.
Understanding_Digital_Forensics_Presentation.pptx
Spectral efficient network and resource selection model in 5G networks
How UI/UX Design Impacts User Retention in Mobile Apps.pdf
Build a system with the filesystem maintained by OSTree @ COSCUP 2025
Mobile App Security Testing_ A Comprehensive Guide.pdf
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
sap open course for s4hana steps from ECC to s4
Machine learning based COVID-19 study performance prediction
ACSFv1EN-58255 AWS Academy Cloud Security Foundations.pptx
NewMind AI Weekly Chronicles - August'25 Week I

Natural Language Processing - Groupings (Associations) Generation

  • 1. Groupings (Associations) Generation Natural Language Processing Andrew Ferlitsch Quisse.Com
  • 2. Problem • Develop a method to automate the generation of Associations (Groupings). • Used to teach associations between objects to pre-school and early school children. • Ex. • What item does not belong? Cat, Dog, Fire Truck, Bird
  • 3. Premise At a young age, we train children initially through rote memorization via trial and error and correction by the adult. When we advance to associations, we are developing their ability to learn from abstraction; that is, how do items relate to each other. In this process, we are use the method of categorical separation. We start with categories that are far apart; thus a child will recognize that a car (category = transportation) is too distant from cat, dog, hamster (category = animal) without yet recognizing the finer relationship of the grouping being household pets. As they succeed at recognizing this coarse level of categorical separation, we narrow the categorical hierarchy to learn how within a category the items are related, to learn less coarse relationships.
  • 4. Categorical Dictionary - Category { noun: ‘cat’, category: ‘Animal’ }, { noun: ‘dog’, category: ‘Animal’}, { noun: ‘pig’, category: ‘Animal’}, { noun: ‘hamster’, category: ‘Animal’}, { noun: ‘car’, category: ‘Transportation’}, { noun: ‘airplane’, category: ‘Transportation’}, { noun: ‘firetruck’, category: ‘Transportation’} A categorical dictionary consists of three levels. Each entry (e.g., noun) is first differentiated with a top-level category. For example, a noun being either an Animal or Transportation.
  • 5. Categorical Dictionary - Major { noun: ‘cat’, category: ‘Animal’, major: ‘Mammal’ }, { noun: ‘dog’, category: ‘Animal’, major: ‘Mammal’}, { noun: ‘pig’, category: ‘Animal’, major: ‘Mammal’}, { noun: ‘tiger’, category: ‘Animal’, major: ‘Mammal’}, { noun: ‘hamster’, category: ‘Animal’, major: ‘Mammal’}, { noun: ‘penguin’, category: ‘Animal’, major: ‘Bird’}, { noun: ‘snake’, category: ‘Animal’, major: ‘Reptile’}, { noun: ‘car’, category: ‘Transportation’, major: ‘Land’}, { noun: ‘firetruck’, category: ‘Transportation’, major: ‘Land’}, { noun: ‘airplane’, category: ‘Transportation’, major: ‘Air’}, { noun: ‘boat’, category: ‘Transportation’, major: ‘Water’}, For each entry in the categorical dictionary, a second property (‘major’) was added for the next categorical level to form a two-tier hierarchy. For example, for Animal, we have a major subcategory of mammal, fish, bird, reptile, and amphibian.
  • 6. Categorical Dictionary - Minor { noun: ‘cat’, category: ‘Animal’, major: ‘Mammal’, minor: ‘Pet’ }, { noun: ‘dog’, category: ‘Animal’, major: ‘Mammal’, minor: ‘Pet’}, { noun: ‘pig’, category: ‘Animal’, major: ‘Mammal’, minor: ‘Farm’}, { noun: ‘tiger’, category: ‘Animal’, major: ‘Mammal’, minor: ‘Wild’}, { noun: ‘hamster’, category: ‘Animal’, major: ‘Mammal’, minor: ‘Pet’}, { noun: ‘penguin’, category: ‘Animal’, major: ‘Bird’, minor: ‘Wild’}, For each entry in the categorical dictionary, a third property (‘minor’) was added for the next categorical level to form a three-tier hierarchy. For example, for Animal->Mammal, we have a minor subcategory of wild, farm and pet.
  • 7. Categorical Dictionary - Blanks { noun: ‘animal’, category: ‘Animal’, major: ‘’, minor: ‘’ }, { noun: ‘bird’, category: ‘Animal’, major: ‘Bird’, minor: ‘’ }, No Distinction No Distinction For some nouns, like bird, there is no distinction beyond the category or major subcategory level. In this case, the next level is left blank.
  • 8. Categorical Dictionary – Multiple Entries For other nouns, they can belong to multiple minor subcategories. For example penguins can be both wild and flightless. In this case, the minor subcategory is a list. { noun: ‘penguin’, category: ‘Animal’, major: ‘Bird’, minor: [ ‘Wild’, ‘Flightless’ ] },
  • 9. Association Dictionary { group: ‘Flightless Birds’, category: ‘Animal’, major: ‘Bird’, minor: ‘Flightless’ }, { group: ‘Birds of Prey’, category: ‘Animal’, major: ‘Bird’, minor: ‘Predator’ }. { group: ‘Farm Animals’, category: ‘Animal’, major: [ ‘Mammal’, ‘Bird’], minor: ‘Farm’ } The construction of the dictionary is similar to that of the categorical dictionary. The group property holds a text string that is the primary key and a description of the association. For each association, the property values for category, major and minor are used to search for entries in the categorical dictionary that would be in the association.
  • 10. Quiz Generation { group: ‘Flightless Birds’, category: ‘Animal’, major: ‘Bird’, minor: ‘Flightless’ } => { noun: ‘hawk’, category: ‘Animal’, major: ‘Bird’, minor: [ ‘Wild’, ‘Predator’ ] }, { noun: ‘falcon’, category: ‘Animal’, major: ‘Bird’, minor: [ ‘Wild’, ‘Predator’ ] }, … For each association selected (e.g., Birds of Prey), the category, and major/ minor subcategories of the association is applied to the categorical dictionary for a matching list of nouns
  • 11. Quiz Generation From the matching list, three nouns are selected by random (e.g., Hawk, Condor, Eagle}. A question is then formed of the following format: Which of the following does not belong? <noun1>, <noun2>, <noun3>, <noun4> An answer is then formed of the following format, where description is the description of the association (e.g., Birds of Prey). A <noun-not> does not belong to the group <description>
  • 12. Level 1 Difficulty At the first level of difficulty, the category of the association (e.g., Animal) is used to search the categorical dictionary for all entries not matching the category. From the resultant matching list, one entry is chosen at random. { group: ‘Flightless Birds’, category: ‘Animal’, major: ‘Bird’, minor: ‘Flightless’ } => { noun: ‘car’, category: ‘Transportation’}, { noun: ‘firetruck’, category: ‘Transportation’} … From the matching list, one noun is randomly selected. The noun is then inserted into the remaining placeholder of the question and <noun-not> placeholder of the answer. Which of the following does not belong? falcon, hawk, firetruck, eagle A firetruck does not belong to the group Birds of Prey.
  • 13. Level 2 Difficulty At the second level of difficulty, the category and the major subcategory of the association (e.g., Animal->Bird) are used to search the categorical dictionary for all entries that match the category, but do not match the major. { group: ‘Flightless Birds’, category: ‘Animal’, major: ‘Bird’, minor: ‘Flightless’ } => { noun: ‘tiger’, category: ‘Animal’, major: ‘Mammal’}, { noun: ‘pig’, category: ‘Animal’, major: ‘Mammal’} … From the matching list, one noun is randomly selected (e.g., tiger). Which of the following does not belong? falcon, tiger, hawk, eagle A tiger does not belong to the group Birds of Prey.
  • 14. Level 3 Difficulty At the third level of difficulty, the category and the major/minor subcategories of the association (e.g., Animal->Bird->Predator) are used to search the categorical dictionary for all entries that match the category and major subcategory, but do not match the minor subcategory. { group: ‘Flightless Birds’, category: ‘Animal’, major: ‘Bird’, minor: ‘Flightless’ } => { noun: ‘parrot’, category: ‘Animal’, major: ‘Bird’, minor: ‘Pet’}, { noun: ‘cockatoo’, category: ‘Animal’, major: ‘Bird’, minor: ‘Pet’} … From the matching list, one noun is randomly selected (e.g., tiger). Which of the following does not belong? falcon, eagle, cockatoo, hawk A cockatoo does not belong to the group Birds of Prey.