A Model of Anaphoric Ambiguities using Sheaf Theoretic Quantum-like Contextuality and BERT

TL;DR

This paper models natural language anaphoric ambiguities using a sheaf-theoretic framework that exhibits quantum-like contextuality, leveraging BERT to identify contextual examples in language corpora, aiming to enhance NLP understanding.

Contribution

It introduces a novel schema for anaphoric ambiguities based on quantum-like contextuality and applies BERT to instantiate and analyze this schema in natural language.

Findings

Discovered numerous sheaf-contextual examples in language data

Demonstrated the applicability of quantum-like models to NLP ambiguities

Provided a framework for future quantum computing applications in NLP

Abstract

Ambiguities of natural language do not preclude us from using it and context helps in getting ideas across. They, nonetheless, pose a key challenge to the development of competent machines to understand natural language and use it as humans do. Contextuality is an unparalleled phenomenon in quantum mechanics, where different mathematical formalisms have been put forwards to understand and reason about it. In this paper, we construct a schema for anaphoric ambiguities that exhibits quantum-like contextuality. We use a recently developed criterion of sheaf-theoretic contextuality that is applicable to signalling models. We then take advantage of the neural word embedding engine BERT to instantiate the schema to natural language examples and extract probability distributions for the instances. As a result, plenty of sheaf-contextual examples were discovered in the natural language corpora BERT utilises. Our hope is that these examples will pave the way for future research and for finding ways to extend applications of quantum computing to natural language processing.