The paper discusses Quantum Natural Language Processing (QNLP) and its application in Coreference Resolution tasks. QNLP represents word meanings as points in a Hilbert space and applies Parametrised Quantum Circuits (PQCs) to these points based on grammatical structure. The approach was tested on a pronoun resolution task using a Variational Quantum Classifier (VQC) for binary classification. The model achieved an F1 score of 87.20%, outperforming classical coreference resolution systems and nearly matching the state-of-the-art SpanBERT. A mixed quantum-classical model further improved these results, with an F1 score increase of around 6%.
Publication date: 4 Dec 2023
Project Page: Unknown
Paper: https://arxiv.org/pdf/2312.00688
