English(EN) STRUCTURALCOST: A controlled reading time dataset for modeling human sentence processing difficulty

新数据集STRUCTURALCOST模拟人类句子处理难度

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-07 04:00

研究人员推出了STRUCTURALCOST，这是一个旨在衡量人类句子处理难度的新数据集，特别关注长距离主谓依赖关系解析。该数据集包含475名参与者和40,800个观察结果，显示人类阅读时间随着依赖关系的长度而增加，受句法嵌入而非仅仅线性距离的影响。虽然包括n-gram、SSM和Transformer架构在内的各种语言模型部分复制了这种难度曲线，但它们低估了人类所经历的整合成本，表明它们捕捉到了预测性方面，但未能捕捉到完整的工作记忆整合成本。 AI

影响提供数据以更好地评估语言模型的认知合理性，并改进它们对人类句子处理的理解。

排序理由该集群包含一篇详细介绍NLP研究新数据集的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍NLP研究新数据集的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Nina Nusbaumer, Iria de-Dios-Flores, Corentin Bel, Christophe Pallier, Guillaume Wisniewski, Beno\^it Crabb\'e · 2026-10-07 04:00

STRUCTURALCOST: 一个用于模拟人类句子处理难度的受控阅读时间数据集

arXiv:2610.08208v1 Announce Type: cross Abstract: We introduce STRUCTURALCOST, a self-paced reading dataset of 475 participants and 40,800 observations isolating the processing cost of long-distance subject-verb dependency resolution. We replicate a low-powered psycholinguistic f…

本文如何被排名

报道来源 [1]

STRUCTURALCOST: 一个用于模拟人类句子处理难度的受控阅读时间数据集

相关实体

相关话题