On the Winograd Schema: Situating Language Understanding in the Data-Information-Knowledge Continuum

TL;DR

This paper analyzes the Winograd Schema challenge by positioning it within the data-information-knowledge continuum, linking it to the missing text phenomenon, and discussing its implications for data-driven language understanding approaches.

Contribution

It formally situates the Winograd Schema in the knowledge continuum, relates it to the missing text phenomenon, and critiques data-driven methods for addressing such challenges.

Findings

Winograd Schema resides in the knowledge part of the continuum.

The missing text phenomenon underpins many language understanding tasks.

Data-driven approaches may be incompatible with handling missing text.

Abstract

The Winograd Schema (WS) challenge, proposed as an al-ternative to the Turing Test, has become the new standard for evaluating progress in natural language understanding (NLU). In this paper we will not however be concerned with how this challenge might be addressed. Instead, our aim here is threefold: (i) we will first formally 'situate' the WS challenge in the data-information-knowledge continuum, suggesting where in that continuum a good WS resides; (ii) we will show that a WS is just special case of a more general phenomenon in language understanding, namely the missing text phenomenon (henceforth, MTP) - in particular, we will argue that what we usually call thinking in the process of language understanding involves discovering a significant amount of 'missing text' - text that is not explicitly stated, but is often implicitly assumed as shared background knowledge; and (iii) we conclude by a brief discussion on why MTP is inconsistent with the data-driven and machine learning approach to language understanding.