Resolution of Difficult Pronouns Using the ROSS Method

TL;DR

This paper introduces the ROSS method, a novel approach for resolving difficult pronouns in natural language understanding by combining entity resolution, inference, and commonsense reasoning using the ROSS framework.

Contribution

It presents a new general and embedded inference method for pronoun resolution that leverages ROSS's ontology and situation models, successfully solving complex Winograd schemas.

Findings

Successfully resolves several Winograd schemas.

Integrates inference with entity and pronoun resolution.

Utilizes ROSS's ontology and situation models effectively.

Abstract

A new natural language understanding method for disambiguation of difficult pronouns is described. Difficult pronouns are those pronouns for which a level of world or domain knowledge is needed in order to perform anaphoral or other types of resolution. Resolution of difficult pronouns may in some cases require a prior step involving the application of inference to a situation that is represented by the natural language text. A general method is described: it performs entity resolution and pronoun resolution. An extension to the general pronoun resolution method performs inference as an embedded commonsense reasoning method. The general method and the embedded method utilize features of the ROSS representational scheme; in particular the methods use ROSS ontology classes and the ROSS situation model. The overall method is a working solution that solves the following Winograd schemas: a) trophy and suitcase, b) person lifts person, c) person pays detective, and d) councilmen and demonstrators.