QuCoWE: Quantum Contrastive Word Embeddings with Variational Circuits for Near-Term Quantum Devices

Rabimba Karanjai, Hemanth Madhavarao, Lei Xu, Weidong Shi Feb 1, 2026
DOI arXiv PDF
BibTeX Citation 
@inproceedings{karanjai2026qucowe,
  title={QuCoWE: Quantum Contrastive Word Embeddings with Variational Circuits for Near-Term Quantum Devices},
  author={Karanjai, Rabimba and Madhavarao, Hemanth Hegadehalli and Xu, Lei and Shi, Weidong},
  booktitle={International Workshop on Quantum Computing and Artificial Intelligence},
  pages={83--100},
  year={2026},
  organization={Springer}
}
Copied to clipboard
Read Paper Download PDF

Abstract

We present QuCoWE a framework that learns quantumnative word embeddings by training shallow hardwareefficient parameterized quantum circuits PQCs with a contrastive skipgram objective Words are encoded by datareuploading circuits with controlled ring entanglement similarity is computed via quantum state fidelity and passed through a logitfidelity head that aligns scores with the shiftedPMI scale of SGNSNoiseContrastive Estimation To maintain trainability we introduce an entanglementbudget regularizer based on singlequbit purity that mitigates barren plateaus On Text8 and WikiText2 QuCoWE attains competitive intrinsic WordSim353 SimLex999 and extrinsic SST2 TREC6 performance versus 50100d classical baselines while using fewer learned parameters per token All experiments are run in classical simulation we analyze depolarizingreadout noise and include errormitigation hooks zeronoise extrapolation randomized compiling to facilitate hardware deployment

Type Conference Paper
Venue International Workshop on Quantum Computing and Artificial Intelligence
Date Feb 2026
Quantum Computing NLP Word Embeddings First Author
Quantum Computing NLP Word Embeddings First Author