ChronoLens：跨时间、跨语言与跨层面的语言演变测量

摘要

历史语言变化影响形态学、句法学、语义学和语用学，然而计算研究通常使用不相容的表示方法来考察这些层面，因此无法确定它们在不同语言中是否共同演化。我们通过在单一分析空间内考察变化的幅度和方向如何跨语言层面、跨语言、跨历史时期变化来应对这一问题。我们提出ChronoLens框架，该框架结合了冻结多语言语言模型、特征对齐交叉解码器（feature-aligned crosscoders）和事后语言干预（post-hoc linguistic interventions），并将其应用于来自五个议会传统、涵盖1803年至2026年的4498万篇文档、约172亿词元。由此产生的稀疏表示与语言学统计量的一致性显著强于稠密嵌入或池化稀疏自编码器（ρ=0.72对0.29和0.28），并揭示出形态学、句法学、语义学和语用学在同一语言内的变化幅度总体相当，而不同语言在变化时间、变化程度和变化方向上存在显著差异。这些发现表明，历史语言变化是一个结构化的多维过程：相似的变化幅度可能掩盖不同的变化轨迹，而有意义的跨语言比较需要同时衡量距离和方向。

English

Historical language change affects morphology, syntax, semantics, and pragmatics, yet computational studies typically examine these levels with incompatible representations and therefore cannot determine whether they evolve together across languages. We address this problem by asking how the magnitude and direction of change vary across linguistic levels, languages, and historical periods within a single analytical space. We introduce ChronoLens, a framework that combines frozen multilingual language models, feature-aligned crosscoders, and post-hoc linguistic interventions, and apply it to 44.98 million documents and approximately 17.2 billion tokens from five parliamentary traditions spanning 1803--2026. The resulting sparse representations agree substantially more strongly with linguistic statistics than dense embeddings or a pooled sparse autoencoder (ρ=0.72 versus 0.29 and 0.28), and reveal that morphology, syntax, semantics, and pragmatics generally change by comparable amounts within a language, while languages differ markedly in when, how far, and in which direction they change. These findings show that historical language change is a structured, multidimensional process: similar magnitudes can conceal different trajectories, and meaningful cross-linguistic comparison requires measuring both distance and direction.