Automating the encoding for the LISA model of analogy from raw text

Sean Wilner, J. E. Hummel

Research output: Contribution to conferencePaper

Abstract

Analogy is an integral part of human cognition. Consequently researchers would like to produce computational models of analogy to test implementations of theoretical claims. Such computational models have relied almost exclusively upon hand-coded representations, making the resulting models too dependent upon the modeler's choices, and thus difficult to interpret in isolation of the modeler. In an effort to combat this dependency, we present here a means of automatic encoding for the LISA model of analogy and inference.

Original languageEnglish (US)
Pages115-122
Number of pages8
StatePublished - Jan 1 2017
Event28th Modern Artificial Intelligence and Cognitive Science Conference, MAICS 2017 - Fort Wayne, United States
Duration: Apr 28 2017Apr 29 2017

Other

Other28th Modern Artificial Intelligence and Cognitive Science Conference, MAICS 2017
CountryUnited States
CityFort Wayne
Period4/28/174/29/17

Keywords

  • Analogy
  • Cognitive Psychology
  • Computational Linguistics
  • Natural Language Processing

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Wilner, S., & Hummel, J. E. (2017). Automating the encoding for the LISA model of analogy from raw text. 115-122. Paper presented at 28th Modern Artificial Intelligence and Cognitive Science Conference, MAICS 2017, Fort Wayne, United States.