Efficient Generation of Parameterised Quantum Circuits from Large Texts
This work addresses the challenge of scaling quantum natural language processing for researchers and practitioners by enabling efficient encoding of long texts, though it is incremental as it builds on existing frameworks like DisCoCirc.
The paper tackles the problem of encoding large-scale texts into parameterised quantum circuits efficiently, achieving the ability to handle documents up to 6410 words in experiments.
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.