Exploring a Multidimensional Representation of Documents and Queries (extended version)

TL;DR

This paper proposes representing documents and queries as multidimensional objects using a quantum-inspired formalism to enhance interactivity in information retrieval systems, and demonstrates its competitive performance through experiments.

Contribution

It introduces a novel multidimensional representation of documents and queries based on quantum formalism for interactive IR systems, with experimental validation.

Findings

Multidimensional representations can compete with standard IR methods.

Parameter settings significantly affect document ranking outcomes.

The approach shows promise for fully interactive IR systems.

Abstract

In Information Retrieval (IR), whether implicitly or explicitly, queries and documents are often represented as vectors. However, it may be more beneficial to consider documents and/or queries as multidimensional objects. Our belief is this would allow building "truly" interactive IR systems, i.e., where interaction is fully incorporated in the IR framework. The probabilistic formalism of quantum physics represents events and densities as multidimensional objects. This paper presents our first step towards building an interactive IR framework upon this formalism, by stating how the first interaction of the retrieval process, when the user types a query, can be formalised. Our framework depends on a number of parameters affecting the final document ranking. In this paper we experimentally investigate the effect of these parameters, showing that the proposed representation of documents and queries as multidimensional objects can compete with standard approaches, with the additional prospect to be applied to interactive retrieval.