Teaching Machines to Learn by Metaphors Omer Levy

Teaching Machines to Learn by Metaphors Omer Levy & Shaul Markovitch Technion – Israel Institute of Technology

Concept Learning by Induction

Few Examples

Transfer Learning Target (New) Source (Original)

Define: Related Concept

Transfer Learning Approaches • Common Inductive Bias • Common Instances • Common Features

Different Feature Space

Example -3 -2 0 2 3

Example -3 -2 0 0 2 3 4 9

Example -3 -2 0 0 2 3 4 9

Common Inductive Bias -3 -2 0 0 2 3 4 9

Common Inductive Bias -3 -2 0 0 2 3 4 9

Common Instances -3 -2 0 0 2 3 4 9

Common Features 3 2 -2 -3 4 9

New Approach to Transfer Learning

Our Solution: Metaphors

Metaphors Target (New) Source (Original)

Source Concept Learner Target Metaphor Learner +/-

Theorem •

The Metaphor Theorem •

Redefine Transfer Learning •

Redefine Transfer Learning •

Metaphor Learning Framework

Concept Learning Framework Search Algorithm Hypothesis Space Data Evaluation Function

Metaphor Learning Framework Source Search Algorithm Metaphor Space Target Evaluation Function

Metaphor Evaluation

Metaphor Evaluation •

Metaphor Evaluation •

Metaphor Evaluation

Metaphor Evaluation

Metaphor Evaluation

Metaphor Evaluation

Metaphor Spaces

Metaphor Spaces • General • Few Degrees of Freedom • Representation-Specific Bias

Geometric Transformations Я R

Dictionary-Based Metaphors cheese queso

Linear Transformations •

Which metaphor space should I use?

Which metaphor space should I use? Automatic Selection of Metaphor Spaces

Which metaphor space should I use? Automatic Selection of Metaphor Spaces Occam’s Razor

Which metaphor space should I use? Automatic Selection of Metaphor Spaces Occam’s Razor Structural Risk Minimization

Automatic Selection of Metaphor Spaces

Automatic Selection of Metaphor Spaces

Automatic Selection of Metaphor Spaces

Empirical Evaluation

Reference Methods Baseline • Target Only • Identity Metaphor • Merge State-of-the-Art • Frustratingly Easy Domain Adaptation – Daumé, 2007 • Multi. Task Learning – Caruana, 1997; Silver et al, 2010 • Tr. Ada. Boost – Dai et al, 2007

Digits: Negative Image

Digits: Negative Image

Digits: Negative Image

Digits: Higher Resolution

Digits: Higher Resolution

Digits: Higher Resolution

Wine

Wine

Qualitative Results Transfer Learning Target Task Instance Digits: Negative Image Digits: Higher Resolution Target Sample Size 1 2 5 10

Discussion

Recap • Problem: Concept learning with few examples • Solution: Metaphors

Recap •

Recap •

Recap •

Recap •

What if the concepts are not related?

What if the concepts are not related?

Metaphors are not a measure of relatedness

Metaphors are not a measure of relatedness Metaphors explain how concepts are related

Vision

METAPHORS Explaining how concepts are related since 2012.