Interpreting Winograd Schemas Via the SP Theory of Intelligence and Its Realisation in the SP Computer Model

TL;DR

This paper explores how the SP System can interpret Winograd Schemas by recognizing patterns of linguistic associations, highlighting its potential and current limitations in learning the necessary knowledge for disambiguation tasks.

Contribution

It demonstrates the application of the SP System to Winograd Schema interpretation and discusses its strengths and limitations in learning relevant linguistic associations.

Findings

The SP System can recognize patterns of linguistic associations.

It currently requires pre-supplied knowledge for Winograd Schema interpretation.

Potential exists for the SP System to learn the necessary associations in the future.

Abstract

In 'Winograd Schema' (WS) sentences like "The city councilmen refused the demonstrators a permit because they feared violence" and "The city councilmen refused the demonstrators a permit because they advocated revolution", it is easy for adults to understand what "they" refers to but can be difficult for AI systems. This paper describes how the SP System -- outlined in an appendix -- may solve this kind of problem of interpretation. The central idea is that a knowledge of discontinuous associations amongst linguistic features, and an ability to recognise such patterns of associations, provides a robust means of determining what a pronoun like "they" refers to. For any AI system to solve this kind of problem, it needs appropriate knowledge of relevant syntax and semantics which, ideally, it should learn for itself. Although the SP System has some strengths in unsupervised learning, its capabilities in this area are not yet good enough to learn the kind of knowledge needed to interpret WS examples, so it must be supplied with such knowledge at the outset. However, its existing strengths in unsupervised learning suggest that it has potential to learn the kind of knowledge needed for the interpretation of WS examples. In particular, it has potential to learn the kind of discontinuous association of linguistic features mentioned earlier.