变分量子Transformer架构用于合成语言生成
Variational Quantum Transformer Architecture for Synthetic Language Generation
浏览论文内容
中文总结 AI 辅助
本文提出一种NISQ兼容的变分量子Transformer架构用于合成语言生成，通过量子编码器和解码器块实现自回归建模，在语法生成任务上验证了可训练性，但性能不及经典基线，不声称量子优势。
中文摘要 AI 辅助
我们提出了一种紧凑的、兼容NISQ的量子Transformer架构，用于合成QNLP序列建模。该模型保留了经典Transformer的自回归下一个词元接口，但将注意力子层和前馈子层替换为变分量子编码器块、连接电路、解码器块以及直接的双量子比特测量读出。词元上下文被角度编码到小型量子寄存器中，通过并行变分头部和编码器集成电路处理，并通过解码器辅助比特进行条件化，以产生四个词元词汇表上的分布。我们在确定性和词典语法生成任务上评估了多种架构变体，并与紧凑的经典Transformer基线进行比较。量子模型可端到端训练，并学习到非平凡的语法结构，包括在个别运行中实现完美的确定性生成，以及在最强变体中实现高词典有效性。经典基线在准确性和稳定性上仍更优，且量子模型对初始化敏感。因此，本贡献并非声称量子优势，而是提出一种具体的架构，并在近期量子约束下对受Transformer启发的QNLP序列建模进行评估。
英文摘要
We propose a compact NISQ-compatible quantum transformer architecture for synthetic QNLP sequence modelling. The model preserves the autoregressive next-token interface of a classical transformer, but replaces attention and feed-forward sublayers with variational quantum encoder blocks, connector circuits, decoder blocks and a direct two-qubit measurement readout. Token contexts are angle-encoded into small quantum registers, processed by parallel variational heads and encoder integration circuits and conditioned through decoder ancillae to produce a distribution over a four-token vocabulary. We evaluate several architecture variants on deterministic and lexicographic grammar-generation tasks against a compact classical transformer baseline. The quantum models are trainable end-to-end and learn nontrivial grammar structure, including perfect deterministic generation in individual runs and high lexicographic validity in the strongest variant. The classical baseline remains more accurate and stable and the quantum models are sensitive to initialization. The contribution is therefore not a claim of quantum advantage, but a concrete architecture and evaluation of transformer-inspired QNLP sequence modelling under near-term quantum constraints.
发表机构
- Institute of Informatics, LMU Munich（慕尼黑大学信息学院 (LMU Munich 信息学院)）
机构由 AI 辅助整理，请以论文原文为准。
