Category Theory for Quantum Natural Language Processing

• URL: http://arxiv.org/abs/2212.06615v1
• Date: Tue, 13 Dec 2022 14:38:57 GMT
• Title: Category Theory for Quantum Natural Language Processing
• Authors: Alexis Toumi
• Abstract summary: This thesis introduces quantum natural language processing (QNLP) models based on an analogy between computational linguistics and quantum mechanics. The grammatical structure of text and sentences connects the meaning of words in the same way that entanglement structure connects the states of quantum systems. We turn this abstract analogy into a concrete algorithm that translates the grammatical structure onto the architecture of parameterised quantum circuits. We then use a hybrid classical-quantum algorithm to train the model so that evaluating the circuits computes the meaning of sentences in data-driven tasks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This thesis introduces quantum natural language processing (QNLP) models based on a simple yet powerful analogy between computational linguistics and quantum mechanics: grammar as entanglement. The grammatical structure of text and sentences connects the meaning of words in the same way that entanglement structure connects the states of quantum systems. Category theory allows to make this language-to-qubit analogy formal: it is a monoidal functor from grammar to vector spaces. We turn this abstract analogy into a concrete algorithm that translates the grammatical structure onto the architecture of parameterised quantum circuits. We then use a hybrid classical-quantum algorithm to train the model so that evaluating the circuits computes the meaning of sentences in data-driven tasks. The implementation of QNLP models motivated the development of DisCoPy (Distributional Compositional Python), the toolkit for applied category theory of which the first chapter gives a comprehensive overview. String diagrams are the core data structure of DisCoPy, they allow to reason about computation at a high level of abstraction. We show how they can encode both grammatical structures and quantum circuits, but also logical formulae, neural networks or arbitrary Python code. Monoidal functors allow to translate these abstract diagrams into concrete computation, interfacing with optimised task-specific libraries. The second chapter uses DisCopy to implement QNLP models as parameterised functors from grammar to quantum circuits. It gives a first proof-of-concept for the more general concept of functorial learning: generalising machine learning from functions to functors by learning from diagram-like data. In order to learn optimal functor parameters via gradient descent, we introduce the notion of diagrammatic differentiation: a graphical calculus for computing the gradients of parameterised diagrams.

Related papers

• Scalable and interpretable quantum natural language processing: an implementation on trapped ions [1.0037949839020768]
  We present the first implementation of text-level quantum natural language processing. We focus on the QDisCoCirc model, which is underpinned by a compositional approach to rendering AI interpretable. We demonstrate an experiment on Quantinuum's H1-1 trapped-ion quantum processor.
  arXiv  Detail & Related papers  (2024-09-13T12:36:14Z)
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [63.733312560668274]
  Given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties? We prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d. We devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to scaling in many practical settings.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• Quantum Algorithms for Compositional Text Processing [1.3654846342364308]
  We focus on the recently proposed DisCoCirc framework for natural language, and propose a quantum adaptation, QDisCoCirc. This is motivated by a compositional approach to rendering AI interpretable. For the model-native primitive operation of text similarity, we derive quantum algorithms for fault-tolerant quantum computers.
  arXiv  Detail & Related papers  (2024-08-12T11:21:40Z)
• Hybrid Quantum-Classical Machine Learning with String Diagrams [49.1574468325115]
  This paper develops a formal framework for describing hybrid algorithms in terms of string diagrams. A notable feature of our string diagrams is the use of functor boxes, which correspond to a quantum-classical interfaces.
  arXiv  Detail & Related papers  (2024-07-04T06:37:16Z)
• Compilation of algorithm-specific graph states for quantum circuits [55.90903601048249]
  We present a quantum circuit compiler that prepares an algorithm-specific graph state from quantum circuits described in high level languages. The computation can then be implemented using a series of non-Pauli measurements on this graph state.
  arXiv  Detail & Related papers  (2022-09-15T14:52:31Z)
• A gentle introduction to Quantum Natural Language Processing [0.0]
  The main goal of this master's thesis is to introduce Quantum Natural Language Processing. QNLP aims at representing sentences' meaning as vectors encoded into quantum computers.
  arXiv  Detail & Related papers  (2022-02-23T20:17:00Z)
• Benchmarking Small-Scale Quantum Devices on Computing Graph Edit Distance [52.77024349608834]
  Graph Edit Distance (GED) measures the degree of (dis)similarity between two graphs in terms of the operations needed to make them identical. In this paper we present a comparative study of two quantum approaches to computing GED.
  arXiv  Detail & Related papers  (2021-11-19T12:35:26Z)
• LQP: The Dynamic Logic of Quantum Information [77.34726150561087]
  This paper introduces a dynamic logic formalism for reasoning about information flow in composite quantum systems. We present a finitary syntax, a relational semantics and a sound proof system for this logic. As applications, we use our system to give formal correctness for the Teleportation protocol and for a standard Quantum Secret Sharing protocol.
  arXiv  Detail & Related papers  (2021-10-04T12:20:23Z)
• QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computer [0.7194733565949804]
  We present results on the first NLP experiments conducted on Noisy Intermediate-Scale Quantum (NISQ) computers. We create representations for sentences that have a natural mapping to quantum circuits. We successfully train NLP models that solve simple sentence classification tasks on quantum hardware.
  arXiv  Detail & Related papers  (2021-02-25T13:37:33Z)
• Quantum Natural Language Processing on Near-Term Quantum Computers [0.0]
  We describe a full-stack pipeline for natural language processing on near-term quantum computers, aka QNLP. DisCoCat is a language-modelling framework that extends and complements the compositional structure of pregroup grammars. We present a method for mapping DisCoCat diagrams to quantum circuits.
  arXiv  Detail & Related papers  (2020-05-08T16:42:54Z)
• PBS-Calculus: A Graphical Language for Coherent Control of Quantum Computations [77.34726150561087]
  We introduce the PBS-calculus to represent and reason on quantum computations involving coherent control of quantum operations. We equip the language with an equational theory, which is proved to be sound and complete. We consider applications like the implementation of controlled permutations and the unrolling of loops.
  arXiv  Detail & Related papers  (2020-02-21T16:15:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.