基本信息
- 来源: arxiv
- 原始来源: https://arxiv.org/abs/2602.17653v1
- 作者: Iskar Deng, Nathalia Xu, Shane Steinert-Threlkeld
- 分类: cs.CL
- 论文时间: 2026-02-19T18:56:34Z
- 论文 PDF: https://arxiv.org/pdf/2602.17653v1.pdf
来源摘要/节选
Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic regularities in human languages, particularly for syntactic phenomena such as word order. In this paper, we extend this paradigm to differential argument marking (DAM), a semantic licensing system in which morphological marking depends on semantic prominence. Using a controlled synthetic learning method, we train GPT-2 models on 18 corpora implementing distinct DAM systems and evaluate their generalization using minimal pairs. Our results reveal a dissociation between two typological dimensions of DAM. Models reliably exhibit human-like preferences for natural markedness direction, favoring systems in which overt marking targets semantically atypical arguments. In contrast, models do not reproduce the strong object preference in human languages, in which overt marking in DAM more often targets objects rather than subjects. These findings suggest that different typological tendencies may arise from distinct underlying sources.
来源说明
当前只保存了官方论文摘要，不代表论文全文。请以原始来源为准。
本页只呈现已做哈希绑定的来源证据，不包含基于旧正文或缺失原文的扩展推断。