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

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.

arXiv comment38 pages

References in corpus (28)

• Quantum Computing in the NISQ era and beyond
• Supervised learning with quantum enhanced feature spaces
• A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
• Noisy intermediate-scale quantum (NISQ) algorithms
• Quantum machine learning in feature Hilbert spaces
• The power of quantum neural networks
• Efficient Learning for Deep Quantum Neural Networks
• t$|$ket$⟩$ : A Retargetable Compiler for NISQ Devices
• Quantum memories at finite temperature
• Experimental Support for a Categorical Compositional Distributional Model of Meaning
• Supervised quantum machine learning models are kernel methods
• Low-depth gradient measurements can improve convergence in variational hybrid quantum-classical algorithms
• Mathematical Foundations for a Compositional Distributional Model of Meaning
• The Frobenius anatomy of word meanings I: subject and object relative pronouns
• A measurement-based variational quantum eigensolver
• Quantum Algorithms for Compositional Natural Language Processing
• A Study of Entanglement in a Categorical Framework of Natural Language
• Quantum Language Model with Entanglement Embedding for Question Answering
• The Frobenius anatomy of word meanings II: possessive relative pronouns
• DisCoPy: Monoidal Categories in Python
• Grammar-aware sentence classification on quantum computers
• Sentence Entailment in Compositional Distributional Semantics
• A hybrid classical-quantum workflow for natural language processing
• Graded Entailment for Compositional Distributional Semantics
• Foundations for Near-Term Quantum Natural Language Processing
• Quantum Language Processing
• Language Design as Information Renormalization
• A CCG-Based Version of the DisCoCat Framework

Cited by in corpus (21)

• Quantum Machine Learning: from physics to software engineering
• NISQ Computers: A Path to Quantum Supremacy
• Applying QNLP to sentiment analysis in finance
• Quantum Natural Language Processing
• Quantum Picturalism: Learning Quantum Theory in High School
• A CCG-Based Version of the DisCoCat Framework
• How to Sum and Exponentiate Hamiltonians in ZXW Calculus
• lambeq: An Efficient High-Level Python Library for Quantum NLP
• Something Old, Something New: Grammar-based CCG Parsing with Transformer Models
• Differentiating and Integrating ZX Diagrams with Applications to Quantum Machine Learning
• Property-guided Inverse Design of Metal-Organic Frameworks Using Quantum Natural Language Processing
• A Survey of Classical And Quantum Sequence Models
• Quantum Algorithms for Compositional Text Processing
• Perspectives on Utilization of Measurements in Quantum Algorithms
• Experimentally validated quantum-secure federated learning over a multi-user quantum network
• SQL2Circuits: Estimating Cardinalities, Execution Times, and Costs for SQL Queries with Quantum Natural Language Processing
• Lambek pregroups are Frobenius spiders in preorders
• Transformer fault diagnosis using an efficient simulation-driven variational quantum classifier with domain-aware feature encoding
• Density Matrices for Metaphor Understanding
• Grover's Algorithm for Question Answering
• Should Semantic Vector Composition be Explicit? Can it be Linear?