语言模型作为探究可能与不可能自然语言区别的工具
Language models as tools for investigating the distinction between possible and impossible natural languages
AI总结:
本文探讨语言模型作为探究可能与不可能自然语言区别的工具,通过改进模型架构来揭示人类语言学习的归纳偏见。
摘要:
我们主张语言模型(LMs)有潜力作为探究可能与不可能自然语言区别的调查工具,从而揭示支持人类语言学习的归纳偏见。我们概述了一个分阶段的研究计划,在其中LM架构被迭代改进以更好地区分可能与不可能的语言,从而将假设与人类认知联系起来。
英文摘要:
We argue that language models (LMs) have strong potential as investigative tools for probing the distinction between possible and impossible natural languages and thus uncovering the inductive biases that support human language learning. We outline a phased research program in which LM architectures are iteratively refined to better discriminate between possible and impossible languages, supporting linking hypotheses to human cognition.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。