Solving Interpretation Problems With Etcetera Abduction

Abstract

Among the most challenging problems in Artificial Intelligence are those that require human-like abilities to make sense of ambiguous observations, to interpret events in context given a wealth of life experiences and commonsense knowledge. In the 1990s, Jerry Hobbs and colleagues demonstrated how interpretation problems can be tackled with logical abduction, a combinatorial search for the best set of assumptions that logically entails the observations. Etcetera Abduction is a new approach to ranking assumptions by reifying the uncertainty of knowledge base axioms as etcetera literals, representing conditional and prior probabilities that can be combined through logical unification. In this invited talk, I will highlight some of the features of Etcetera Abduction that make it attractive compared to alternatives, and share my perspective on the role of logic-based reasoning given current trends in machine learning research.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2017
Accession Number
AD1159678

Entities

People

  • Andrew S. Gordon

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Autonomy
  • Biomedical

DTIC Thesaurus Topics

  • Abstracts
  • Artificial Intelligence
  • Cognition
  • Crime
  • Formal Languages
  • Images
  • Language
  • Learning
  • Machine Learning
  • Military Research
  • Observation
  • Probability
  • Psychological Theory
  • Reasoning
  • Scientific Theories
  • Standards
  • Uncertainty

Readers

  • Military History of the United States in the 20th Century.
  • Mycotoxin ecology in Amazonian ecosystems.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML