arXiv cs.CL· Iskar Deng, Shane Steinert-Threlkeld·· 12 小时前AI 评分18
从平行到分化：语言模型如何学习动作名词化构式
From Parallels to Divergence: Language Models' Learning of Action Nominal Constructions
AI 导读
研究用语法工程方法构建 96 种合成语言，覆盖小句语序、名词短语语序、对齐、补语系统和 ANC 策略等差异，每种语言从零训练 GPT-2-small，并用覆盖 34 种语法现象的定向最小对进行评测。结果显示模型在小句基本配置上与自然语言的类型学分布平行，但在补语系统和 ANC 策略上出现分化，还会学到自然语言中罕见甚至未见的组合。
正文 · 原文
Abstract:Action nominal constructions (ANCs) express events in nominal form, with their argument marking following patterns found in clauses or ordinary noun phrases. In this paper, we investigate how different grammatical configurations affect language models' learning of ANCs and related constructions, and how these learning preferences compare with typological distributions in natural languages. We use a grammar-engineered method for synthetic corpus construction that combines shared semantic input from natural corpora with computational grammars. We construct 96 target languages varying in clause word order, noun-phrase word order, alignment, complement system, and ANC strategy. For each language, we train GPT-2-small models from scratch and evaluate them using targeted minimal pairs covering 34 grammatical phenomena. The results show typological parallels in basic clause configurations but divergences in complement systems and ANC strategies, with models also learning combinations rare or unattested in natural languages. This partial alignment suggests that natural language distributions may reflect both general learning pressures and functional demands not fully captured by model learning experiments.
| Comments: | 41 pages, including appendices |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22468 [cs.CL] |
| (or arXiv:2610.22468v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22468 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Iskar Deng [view email]
[v1]
Thu, 15 Oct 2026 17:43:47 UTC (566 KB)
来源：arXiv cs.CL · arxiv.org