仅用1比特信号训练神经元细胞自动机，竟自发产生类似语法解析的结构。
On the Emergence of Syntax by Means of Local Interaction
- 用18,658参数的二维神经细胞自动机，通过1比特边界信号训练。
- 自组织形成名为Proto-CKY的结构，与语法结构相关性达r≈0.71。
- 可跨不同文法通用，且扰动后能自发恢复，适合研究语言涌现。
语法处理能否仅通过局部交互自发产生？我们在一个极简系统中给出实例：一个18,658参数的二维神经细胞自动机（NCA），仅以1比特边界信号作为监督，在算术表达式文法的成员判定问题上进行训练。训练完成后，其内部的$L \times L$网格自发组织为一种有序、空间扩展的表示，命名为Proto-CKY。该表示满足三个语法处理操作标准：超越正则语言的表达能力，对训练分布外结构具备泛化能力，且内部组织与语法结构呈定量一致（皮尔逊相关系数$r \approx 0.71$）。Proto-CKY在四种上下文无关文法下均独立出现，并在受扰后可自发再生。它在功能上与CKY算法对齐，但形式上不同于该算法：它是数学理想在物理基底上的具体原型，二者间的系统性差异携带了关于基底本身的信息。
原文摘要 · Abstract (English)
Can syntactic processing emerge spontaneously from purely local interaction? We present a concrete instance on a minimal system: an 18,658-parameter two-dimensional neural cellular automaton (NCA), supervised by nothing more than a 1-bit boundary signal, is trained on the membership problem of an arithmetic-expression grammar. After training, its internal $L \times L$ grid spontaneously self-organizes into an ordered, spatially extended representation that we name Proto-CKY. This representation satisfies three operational criteria for syntactic processing: expressive power beyond the regular languages, structural generalization beyond the training distribution, and an internal organization quantitatively aligned with grammatical structure (Pearson $r \approx 0.71$). It emerges independently on four context-free grammars and regenerates spontaneously after perturbation. Proto-CKY is functionally aligned with the CKY algorithm but formally distinct from it: it is a physical prototype, a concrete instantiation of a mathematical ideal on a physical substrate, and the systematic distance between the two carries information about the substrate itself.
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。