QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computer

TL;DR

This paper demonstrates the first NLP experiments on NISQ quantum computers using compositional models of meaning, showing successful training and convergence on simple sentence classification tasks, and aims to guide AI researchers in quantum NLP.

Contribution

It introduces a quantum-compatible sentence representation based on compositional models, enabling NLP tasks on quantum hardware and providing a practical framework for future quantum NLP research.

Findings

Models converge smoothly in simulations and on quantum hardware.

Syntax-sensitive models outperform syntax-agnostic baselines.

Quantum models successfully classify simple sentences.

Abstract

Quantum Natural Language Processing (QNLP) deals with the design and implementation of NLP models intended to be run on quantum hardware. In this paper, we present results on the first NLP experiments conducted on Noisy Intermediate-Scale Quantum (NISQ) computers for datasets of size greater than 100 sentences. Exploiting the formal similarity of the compositional model of meaning by Coecke, Sadrzadeh and Clark (2010) with quantum theory, we create representations for sentences that have a natural mapping to quantum circuits. We use these representations to implement and successfully train NLP models that solve simple sentence classification tasks on quantum hardware. We conduct quantum simulations that compare the syntax-sensitive model of Coecke et al. with two baselines that use less or no syntax; specifically, we implement the quantum analogues of a "bag-of-words" model, where syntax is not taken into account at all, and of a word-sequence model, where only word order is respected. We demonstrate that all models converge smoothly both in simulations and when run on quantum hardware, and that the results are the expected ones based on the nature of the tasks and the datasets used. Another important goal of this paper is to describe in a way accessible to AI and NLP researchers the main principles, process and challenges of experiments on quantum hardware. Our aim in doing this is to take the first small steps in this unexplored research territory and pave the way for practical Quantum Natural Language Processing.