Scaling Ontologies with Language Models and Math

Slides presented at the ONTOCHAIN Summit for Trustworthy Internet by Marc Green, Software Architect in Cybersecurity

Transcript

1. Scaling Ontologies
   with Language Models and Math
   marcgreen@wpi.edu
   Marc Green
   

   View Slide

2. Problems
   ● Humanity’s corpus of scientific
   knowledge is not yet robustly linked
   ● Ontology engineering is hard,
   time-consuming, and expensive
   marcgreen@wpi.edu
   Marc Green
   ● Ologs provide mathematical
   robustness to ontologies
   ● Language Models increase
   efficiency and accessibility of
   knowledge workflows
   Solutions
   

   View Slide

3. Intro to Ologs (ontology logs)
   marcgreen@wpi.edu
   - “Rigorous mathematical framework for knowledge representation,
   construction of scientific models, and data storage” (Spivak, 2011)
   - More scalable than traditional semantic web standards like RDF
   Marc Green
   (Spivak, 2011)
   (Spivak, 2011)
   

   View Slide

4. Intro to Language Models (LMs)
   - Enable a new paradigm of Human-Computer Interaction
   - B2C for closed domains (chatbots), B2B for open domains (ai assistants)
   marcgreen@wpi.edu
   Marc Green https://huggingface.co/blog/large-language-models
   

   View Slide

5. Ontochain application idea: Ontology AI Assistant
   - Public service to increase access to and utility of shared understandings
   - Key Ideas:
   - Language Models increase accessibility and improve efficiency of working with text
   - Ologs provide rigorous and scalable mechanism for building shared understandings
   - Potential features:
   - Natural Language UI for interacting with ontologies (querying, editing, aligning, etc)
   - SotA NLP for systematic generation and manipulation of ontologies (eg from existing literature)
   - Integrates with decentralized network, knowledge graph and knowledge/asset market
   - Modular architecture allows app to scale as LM tech improves
   marcgreen@wpi.edu
   Marc Green
   

   View Slide

6. marcgreen@wpi.edu
   Marc Green
   

   View Slide

7. Other References and Related Work
   ● Spivak, 2011: Ologs: a categorical framework for knowledge representation
   (arXiv:1102.1889)
   ● “23% searching …”: https://topos.institute/networked-mathematics
   ● Training and Application of Neural-Network Language Model for Ontology
   Population
   (https://www.researchgate.net/publication/347861342_Training_and_Applicati
   on_of_Neural-Network_Language_Model_for_Ontology_Population)
   ● Ontology-Based Model Abstraction
   (https://www.researchgate.net/publication/332290797_Ontology-Based_Mode
   l_Abstraction)
   ● Semantic Scholar by Allen Institute of AI
   ● MathFoldR by Topos Institute
   marcgreen@wpi.edu
   Marc Green
   

   View Slide