Quantum Recurrent Architectures for Text Classification

Wenduan Xu, Stephen Clark, Douglas Brown, Gabriel Matos, Konstantinos Meichanetzidis


Abstract
We develop quantum RNNs with cells based on Parametrised Quantum Circuits (PQCs). PQCs can provide a form of hybrid quantum-classical computation where the input and the output is in the form of classical data. The previous “hidden” state is the quantum state from the previous time-step, and an angle encoding is used to define a (non-linear) mapping from a classical word embedding into the quantum Hilbert space. Measurements of the quantum state provide classical statistics which are used for classification. We report results which are competitive with various RNN baselines on the Rotten Tomatoes dataset, as well as emulator results which demonstrate the feasibility of running such models on quantum hardware.
Anthology ID:
2024.emnlp-main.1000
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18020–18027
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1000
DOI:
10.18653/v1/2024.emnlp-main.1000
Bibkey:
Cite (ACL):
Wenduan Xu, Stephen Clark, Douglas Brown, Gabriel Matos, and Konstantinos Meichanetzidis. 2024. Quantum Recurrent Architectures for Text Classification. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18020–18027, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Quantum Recurrent Architectures for Text Classification (Xu et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1000.pdf