Multimodal Structure-Aware Quantum Data Processing

TL;DR

This paper introduces MultiQ-NLP, a quantum computing framework for processing multimodal text and image data that captures linguistic and visual structures, achieving competitive results with classical models.

Contribution

It develops a novel quantum-based architecture for structure-aware multimodal data processing, integrating syntactic and visual hierarchies.

Findings

Achieved parity with state-of-the-art classical models on image classification.

Developed fully structured quantum models for multimodal data.

Enhanced translation with new types and homomorphisms.

Abstract

While large language models (LLMs) have advanced the field of natural language processing (NLP), their "black box" nature obscures their decision-making processes. To address this, researchers developed structured approaches using higher order tensors. These are able to model linguistic relations, but stall when training on classical computers due to their excessive size. Tensors are natural inhabitants of quantum systems and training on quantum computers provides a solution by translating text to variational quantum circuits. In this paper, we develop MultiQ-NLP: a framework for structure-aware data processing with multimodal text+image data. Here, "structure" refers to syntactic and grammatical relationships in language, as well as the hierarchical organization of visual elements in images. We enrich the translation with new types and type homomorphisms and develop novel architectures to represent structure. When tested on a main stream image classification task (SVO Probes), our best model showed a par performance with the state of the art classical models; moreover the best model was fully structured.