Emergent Semantics: Meaning and Metaphor

1. Emergent Semantics:Meaning and Metaphor Jay McClelland Department of Psychology andCenter for Mind, Brain, and ComputationStanford University

2. language The Parallel Distributed Processing Approach to Semantic Cognition • Representation is a pattern of activation distributed over neurons within and across brain areas. • Bidirectional propagation of activation underlies the ability to bring these representations to mind from given inputs. • The knowledge underlying propagation of activation is in the connections. • Experience affects our knowledge representations through a gradual connection adjustment process

3. dog goat hammer Distributed Representations:and Overlapping Patterns for Related Concepts dog goat hammer

4. Responses of Four Neurons to Face andNon-Face Stimuli

5. Emergence of Meaning and Metaphor • Learned distributed representations that capture important aspects of meaning emerge through a gradual learning process in simple connectionist networks • Metaphor arises naturally as a byproduct of learning information in homologous domains in models of this type

6. Emergence of Meaning: Differentiation, Domain-Specificity, and Reorganization

8. The Rumelhart Model

9. The Training Data: All propositions true of items at the bottom levelof the tree, e.g.: Robin can {grow, move, fly}

10. Target output for ‘robin can’ input

11. aj wij ai neti=Sajwij wki Forward Propagation of Activation

12. Back Propagation of Error (d) aj wij ai di ~ Sdkwki wki dk ~ (tk-ak) Error-correcting learning: At the output layer: Dwki = edkai At the prior layer: Dwij = edjaj …

15. Early Later LaterStill Experie nce

16. Learning is sensitive to patterns of coherent covariation. Coherent Covariation: The tendency for properties of objects to co-vary in clusters Why Does the Model Show Progressive Differentiation?

17. What Drives Progressive Differentiation? • Waves of differentiation reflect coherent covariation of properties across items. • Patterns of coherent covariation are reflected in the principal components of the property covariance matrix. • Figure shows attribute loadings on the first three principal components: • 1. Plants vs. animals • 2. Birds vs. fish • 3. Trees vs. flowers • Same color = features covary in component • Diff color = anti-covarying features

18. A Sensitivity to Coherence Requires Convergence A A

19. Conceptual Reorganization (Carey, 1985) Carey demonstrated that young children ‘discover’ the unity of plants and animals as living things with many shared properties only around the age of 10. She suggested that the coalescence of the concept of living thing depends on learning about diverse aspects of plants and animals including Nature of life sustaining processes What it means to be dead vs. alive Reproductive properties Can reorganization occur in a connectionist net?

20. Conceptual Reorganization in the Model Suppose superficial appearance information, which is not coherent with much else, is always available… And there is a pattern of coherent covariation across information that is contingently available in different contexts. The model forms initial representations based on superficial appearances. Later, it discovers the shared structure that cuts across the different contexts, reorganizing its representations.

22. Organization of Conceptual Knowledge Early and Late in Development

23. Medial Temporal Lobe Proposed Architecture for the Organization of Semantic Memory name action motion Temporal pole color valance form

24. Metaphor in Connectionist Models of Semantics • By metaphor I mean: the application of a relation learned in one domain to a novel situation in another

25. Person 2 Person 1 Relation Hinton’s Family Tree Network

27. Understanding Via Metaphor in the Family Trees Network Marco’s father is Pierro. Who is James’s father? Christopher’s daughter is Victoria. Who is Roberto’s daughter?

28. Emergence of Meaning and Metaphor • Learned distributed representations that capture important aspects of meaning emerge through a gradual learning process in simple connectionist networks • Metaphor arises naturally as a byproduct of learning information in homologous domains in models of this type