Quantum Methods for Managing Ambiguity in Natural Language Processing

• URL: http://arxiv.org/abs/2504.00040v1
• Date: Sun, 30 Mar 2025 19:10:37 GMT
• Title: Quantum Methods for Managing Ambiguity in Natural Language Processing
• Authors: Jurek Eisinger, Ward Gauderis, Lin de Huybrecht, Geraint A. Wiggins,
• Abstract summary: The Categorical Compositional Distributional (DisCoCat) framework models meaning in natural language.<n>DisCoCat diagrams can be associated with tensor networks and quantum circuits.<n>We show how to create probability distributions on quantum circuits that represent the meanings of sentences.
• Score: 0.5437298646956507
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Categorical Compositional Distributional (DisCoCat) framework models meaning in natural language using the mathematical framework of quantum theory, expressed as formal diagrams. DisCoCat diagrams can be associated with tensor networks and quantum circuits. DisCoCat diagrams have been connected to density matrices in various contexts in Quantum Natural Language Processing (QNLP). Previous use of density matrices in QNLP entails modelling ambiguous words as probability distributions over more basic words (the word \texttt{queen}, e.g., might mean the reigning queen or the chess piece). In this article, we investigate using probability distributions over processes to account for syntactic ambiguity in sentences. The meanings of these sentences are represented by density matrices. We show how to create probability distributions on quantum circuits that represent the meanings of sentences and explain how this approach generalises tasks from the literature. We conduct an experiment to validate the proposed theory.

Related papers

• Conditional Distribution Quantization in Machine Learning [83.54039134248231]
  Conditional expectation mathbbE(Y mid X) often fails to capture the complexity of multimodal conditional distributions mathcalL(Y mid X)<n>We propose using n-point conditional quantizations--functional mappings of X that are learnable via gradient descent--to approximate mathcalL(Y mid X)
  arXiv  Detail & Related papers  (2025-02-11T00:28:24Z)
• Quantization of Large Language Models with an Overdetermined Basis [73.79368761182998]
  We introduce an algorithm for data quantization based on the principles of Kashin representation. Our findings demonstrate that Kashin Quantization achieves competitive or superior quality in model performance.
  arXiv  Detail & Related papers  (2024-04-15T12:38:46Z)
• Connecting classical finite exchangeability to quantum theory [45.76759085727843]
  Exchangeability is a fundamental concept in probability theory and statistics.<n>It allows to model situations where the order of observations does not matter.<n>It is well known that both theorems do not hold for finitely exchangeable sequences.
  arXiv  Detail & Related papers  (2023-06-06T17:15:19Z)
• Advantages of quantum mechanics in the estimation theory [0.0]
  In quantum theory, the situation with operators is different due to its non-commutativity nature. We formulate, with complete generality, the quantum estimation theory for Gaussian states in terms of their first and second moments.
  arXiv  Detail & Related papers  (2022-11-13T18:03:27Z)
• Theory of Quantum Generative Learning Models with Maximum Mean Discrepancy [67.02951777522547]
  We study learnability of quantum circuit Born machines (QCBMs) and quantum generative adversarial networks (QGANs) We first analyze the generalization ability of QCBMs and identify their superiorities when the quantum devices can directly access the target distribution. Next, we prove how the generalization error bound of QGANs depends on the employed Ansatz, the number of qudits, and input states.
  arXiv  Detail & Related papers  (2022-05-10T08:05:59Z)
• Why we should interpret density matrices as moment matrices: the case of (in)distinguishable particles and the emergence of classical reality [69.62715388742298]
  We introduce a formulation of quantum theory (QT) as a general probabilistic theory but expressed via quasi-expectation operators (QEOs) We will show that QT for both distinguishable and indistinguishable particles can be formulated in this way. We will show that finitely exchangeable probabilities for a classical dice are as weird as QT.
  arXiv  Detail & Related papers  (2022-03-08T14:47:39Z)
• Learning with Density Matrices and Random Features [44.98964870180375]
  A density matrix describes the statistical state of a quantum system. It is a powerful formalism to represent both the quantum and classical uncertainty of quantum systems. This paper explores how density matrices can be used as a building block for machine learning models.
  arXiv  Detail & Related papers  (2021-02-08T17:54:59Z)
• Quantum Language Model with Entanglement Embedding for Question Answering [7.398550174147092]
  Quantum Language Models (QLMs) in which words are modelled as quantum superposition of sememes have demonstrated a high level of model transparency and good post-hoc interpretability. We propose a neural network model with a novel Entanglement Embedding (EE) module, whose function is to transform the word sequences into entangled pure states of many-body quantum systems.
  arXiv  Detail & Related papers  (2020-08-23T02:34:26Z)
• Contextuality scenarios arising from networks of stochastic processes [68.8204255655161]
  An empirical model is said contextual if its distributions cannot be obtained marginalizing a joint distribution over X. We present a different and classical source of contextual empirical models: the interaction among many processes. The statistical behavior of the network in the long run makes the empirical model generically contextual and even strongly contextual.
  arXiv  Detail & Related papers  (2020-06-22T16:57:52Z)
• At the Interface of Algebra and Statistics [0.0]
  This thesis takes inspiration from quantum physics to investigate mathematical structure that lies at the interface of algebra and statistics. Every joint probability distribution on a finite set can be modeled as a rank one density operator. We show it is akin to conditional probability, and then investigate the extent to which the eigenvectors capture "concepts" inherent in the original joint distribution.
  arXiv  Detail & Related papers  (2020-04-12T15:22:07Z)

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.