Quantum-Enhanced Natural Language Generation: A Multi-Model Framework with Hybrid Quantum-Classical Architectures
This work addresses the interest in quantum computing for natural language processing, but it is incremental as it primarily compares existing methods on new data without introducing a novel paradigm.
This paper tackles the problem of evaluating quantum text generation models against traditional architectures, finding that while Transformers remain superior overall with an average perplexity of 1.21 and BLEU-1 score of 0.2895, quantum-inspired models like QKSAN and QRWKV show competitive performance in specific scenarios such as zero repetition rates and perfect vocabulary diversity.
This paper presents a comprehensive evaluation of quantum text generation models against traditional Transformer/MLP architectures, addressing the growing interest in quantum computing applications for natural language processing. We conduct systematic experiments comparing five distinct models: Transformer (baseline), Quantum Kernel Self-Attention Network (QKSAN), Quantum RWKV (QRWKV), and Quantum Attention Sequence Architecture (QASA) across five diverse datasets including simple sentences, short stories, quantum phrases, haiku poetry, and proverbs. Our evaluation employs multiple metrics including perplexity, BLEU scores, vocabulary diversity, repetition rates, and fluency measures to assess different aspects of text generation quality. The experimental results reveal that while traditional Transformer models maintain overall superiority with the lowest average perplexity (1.21) and highest BLEU-1 score (0.2895), quantum-inspired models demonstrate competitive performance in specific scenarios. Notably, QKSAN achieves a competitive BLEU-1 score of 0.2800 while maintaining zero repetition rates, and QRWKV demonstrates perfect vocabulary diversity (Distinct-1 = 1.000) in certain tasks.