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

DOI10.1613/JAIR.1.14329arXiv2102.12846OpenAlexW3130183867WikidataQ130915714 ScholiaQ130915714MaRDI QIDQ6135983FDOQ6135983

Author name not available (Why is that?), Dimitri Kartsaklis, Konstantinos Meichanetzidis, Bob Coecke, Author name not available (Why is that?)

Publication date: 28 August 2023

Published in: Journal of Artificial Intelligence Research (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/2102.12846

zbMATH Keywords

natural language

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites Work

• Quantum Computation and Quantum Information
• Reasoning about Meaning in Natural Language with Compact Closed Categories and Frobenius Algebras
• From word to sentence. A computational algebraic approach to grammar
• A practical introduction to tensor networks: Matrix product states and projected entangled pair states
• Quantum Computation and the Evaluation of Tensor Networks
• Quantum neural networks
• String matching in \(\tilde O(\sqrt n+\sqrt m)\) quantum time
• Open System Categorical Quantum Semantics in Natural Language Processing
• The Frobenius anatomy of word meanings I: subject and object relative pronouns
• The Frobenius anatomy of word meanings II: possessive relative pronouns
• Sentence entailment in compositional distributional semantics
• Picturing Quantum Processes
• A Study of Entanglement in a Categorical Framework of Natural Language
• Machine Learning with Quantum Computers
• Title not available (Why is that?)

Cited In (2)

• Quantum computations for disambiguation and question answering
• Fibered universal algebra for first-order logics

This page was built for publication: QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computer

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6135983)