Scalable and interpretable quantum natural language processing: an implementation on trapped ions

• URL: http://arxiv.org/abs/2409.08777v1
• Date: Fri, 13 Sep 2024 12:36:14 GMT
• Title: Scalable and interpretable quantum natural language processing: an implementation on trapped ions
• Authors: Tiffany Duneau, Saskia Bruhn, Gabriel Matos, Tuomas Laakkonen, Katerina Saiti, Anna Pearson, Konstantinos Meichanetzidis, Bob Coecke,
• Abstract summary: 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.
• Score: 1.0037949839020768
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present the first implementation of text-level quantum natural language processing, a field where quantum computing and AI have found a fruitful intersection. We focus on the QDisCoCirc model, which is underpinned by a compositional approach to rendering AI interpretable: the behaviour of the whole can be understood in terms of the behaviour of parts, and the way they are put together. Interpretability is crucial for understanding the unwanted behaviours of AI. By leveraging the compositional structure in the model's architecture, we introduce a novel setup which enables 'compositional generalisation': we classically train components which are then composed to generate larger test instances, the evaluation of which asymptotically requires a quantum computer. Another key advantage of our approach is that it bypasses the trainability challenges arising in quantum machine learning. The main task that we consider is the model-native task of question-answering, and we handcraft toy scale data that serves as a proving ground. We demonstrate an experiment on Quantinuum's H1-1 trapped-ion quantum processor, which constitutes the first proof of concept implementation of scalable compositional QNLP. We also provide resource estimates for classically simulating the model. The compositional structure allows us to inspect and interpret the word embeddings the model learns for each word, as well as the way in which they interact. This improves our understanding of how it tackles the question-answering task. As an initial comparison with classical baselines, we considered transformer and LSTM models, as well as GPT-4, none of which succeeded at compositional generalisation.

Related papers

• 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)
• Sequence Processing with Quantum Tensor Networks [1.534667887016089]
  We introduce complex-valued tensor network models for sequence processing motivated by interpretability and resource compression. We demonstrate experimental results for the task of binary classification of sequences relevant to natural language and bioinformatics. We also demonstrate their implementation on Quantinuum's H2-1 trapped-ion quantum processor, demonstrating the possibility of efficient sequence processing on near-term quantum devices.
  arXiv  Detail & Related papers  (2023-08-15T16:33:39Z)
• A Recursive Bateson-Inspired Model for the Generation of Semantic Formal Concepts from Spatial Sensory Data [77.34726150561087]
  This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data. The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept. The model is able to produce fairly rich yet human-readable conceptual representations without training.
  arXiv  Detail & Related papers  (2023-07-16T15:59:13Z)
• Tensor Networks or Decision Diagrams? Guidelines for Classical Quantum Circuit Simulation [65.93830818469833]
  tensor networks and decision diagrams have independently been developed with differing perspectives, terminologies, and backgrounds in mind. We consider how these techniques approach classical quantum circuit simulation, and examine their (dis)similarities with regard to their most applicable abstraction level. We provide guidelines for when to better use tensor networks and when to better use decision diagrams in classical quantum circuit simulation.
  arXiv  Detail & Related papers  (2023-02-13T19:00:00Z)
• Category Theory for Quantum Natural Language Processing [0.0]
  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.
  arXiv  Detail & Related papers  (2022-12-13T14:38:57Z)
• A didactic approach to quantum machine learning with a single qubit [68.8204255655161]
  We focus on the case of learning with a single qubit, using data re-uploading techniques. We implement the different proposed formulations in toy and real-world datasets using the qiskit quantum computing SDK.
  arXiv  Detail & Related papers  (2022-11-23T18:25:32Z)
• Generalization Metrics for Practical Quantum Advantage in Generative Models [68.8204255655161]
  Generative modeling is a widely accepted natural use case for quantum computers. We construct a simple and unambiguous approach to probe practical quantum advantage for generative modeling by measuring the algorithm's generalization performance. Our simulation results show that our quantum-inspired models have up to a $68 times$ enhancement in generating unseen unique and valid samples.
  arXiv  Detail & Related papers  (2022-01-21T16:35:35Z)
• Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks [86.10875837475783]
  Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. Existing neural models have been shown to lack this basic ability in learning symbolic structures. We propose two auxiliary sequence prediction tasks that track the progress of function and argument semantics.
  arXiv  Detail & Related papers  (2021-09-30T16:41:19Z)
• 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)

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.