用旋量重构词嵌入，提升模型表达力与鲁棒性
A Novel Spinor-Based Embedding Model for Transformers
- 将几何代数中的旋量用于词嵌入编码
- 理论证明旋量可捕捉高维空间复杂关系
- 适合关注表示学习与数学建模的研究者
本文提出一种基于几何代数旋量的新颖词嵌入方法，用于改进Transformer模型。旋量提供丰富的数学框架，能够捕捉高维空间中的复杂关系与变换。通过将词语编码为旋量，旨在增强语言表示的表达能力与鲁棒性。论文阐述了旋量的理论基础，详细说明其在Transformer架构中的集成方式，并讨论潜在优势与挑战。
原文摘要 · Abstract (English)
This paper proposes a novel approach to word embeddings in Transformer models by utilizing spinors from geometric algebra. Spinors offer a rich mathematical framework capable of capturing complex relationships and transformations in high-dimensional spaces. By encoding words as spinors, we aim to enhance the expressiveness and robustness of language representations. We present the theoretical foundations of spinors, detail their integration into Transformer architectures, and discuss potential advantages and challenges.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。