Efficient Generation of Parameterised Quantum Circuits from Large Texts

TL;DR

This paper presents a novel, efficient method for converting large texts into parameterised quantum circuits using tree-like representations, enhancing quantum NLP with improved interpretability and scalability.

Contribution

It introduces a new methodology leveraging symmetric monoidal categories to encode complex texts into quantum circuits, advancing quantum NLP techniques.

Findings

Successfully encoded texts up to 6410 words into quantum circuits

Developed an open-source quantum NLP package, lambeq Gen II

Demonstrated faithful and efficient encoding of syntactic and discourse relations

Abstract

Quantum approaches to natural language processing (NLP) are redefining how linguistic information is represented and processed. While traditional hybrid quantum-classical models rely heavily on classical neural networks, recent advancements propose a novel framework, DisCoCirc, capable of directly encoding entire documents as parameterised quantum circuits (PQCs), besides enjoying some additional interpretability and compositionality benefits. Following these ideas, this paper introduces an efficient methodology for converting large-scale texts into quantum circuits using tree-like representations of pregroup diagrams. Exploiting the compositional parallels between language and quantum mechanics, grounded in symmetric monoidal categories, our approach enables faithful and efficient encoding of syntactic and discourse relationships in long and complex texts (up to 6410 words in our experiments) to quantum circuits. The developed system is provided to the community as part of the augmented open-source quantum NLP package lambeq Gen II.