Towards Literate Artificial Intelligence

Abstract

Standardized tests are used to test students as they progress in the formal education system. These tests are readily available and have clear evaluation procedures. Hence, it has been proposed that these tests can serve as good benchmarks for AI. In this thesis, we propose approaches for solving some common standardized tests taken by students such as reading comprehensions, elementary science exams, geometry questions in the SAT exam and mechanics questions in the AP physics exam. Answering these test problems requires deep linguistic (and sometimes visual) understanding and reasoning capabilities which is challenging for modern AI systems.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2019
Accession Number
AD1167963

Entities

People

  • Mrinmaya Sachan

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Automata Theory
  • Bayesian Networks
  • Cognitive Science
  • Computational Science
  • Computer Languages
  • Computer Vision
  • Data Mining
  • Information Processing
  • Information Science
  • Information Systems
  • Natural Language Processing
  • Network Science
  • Neural Networks
  • Ontologies
  • Reasoning
  • Supervised Machine Learning

Fields of Study

  • Education

Readers

  • Computational Linguistics
  • Psychometric Testing or Psychological Assessment.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy