从平行到分歧：语言模型对动名词化构式的学习
原标题：From Parallels to Divergence: Language Models' Learning of Action Nominal Constructions
AI 摘要
该研究利用语法工程方法构建了96种合成语言，每种语言在从句语序、名词短语语序、配列系统、补语系统和动名词化策略上有所不同，并用BabyLM语料作为共享语义输入，从零训练GPT-2-small模型。通过覆盖34种语法现象的定向最小对评测，发现模型在基本从句配置上表现出与自然语言类型学一致的学习偏好，但在补语系统和动名词化策略上出现分歧，甚至学会自然语言中罕见或未见的组合。这表明自然语言分布可能同时受一般学习压力和模型实验未完全捕捉的功能需求影响。
正文节选
From Parallels to Divergence: Language Models’ Learning of Action Nominal Constructions 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 g