arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.05591cs.CLcs.AIcs.LG
收藏

FLAN-T5中的语义特征验证

Semantic Feature Verification in FLAN-T5

University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Siddharth Suresh, Kushin Mukherjee, Timothy T. Rogers

AI总结:

本研究评估了FLAN-T5在语义特征规范生成中的辅助作用,发现机器验证的规范能捕捉人工规范之外的概念结构信息,并更好地解释远端项目的语义相似性判断,表明大语言模型可显著增强传统语义特征验证方法。

摘要:

本研究评估了大型语言模型在辅助生成语义特征规范方面的潜力,语义特征规范是认知科学中评估概念结构的关键工具。基于现有的人工生成数据集,我们表明,经机器验证的规范能够捕捉到仅靠人工规范无法表达的概念结构方面,并能更好地解释人类对远端相关项目之间语义相似性的判断。结果表明,大型语言模型可以极大地增强传统的语义特征规范验证方法,这对我们理解人类和机器中的概念表征具有重要意义。

英文摘要:

This study evaluates the potential of a large language model for aiding in generation of semantic feature norms - a critical tool for evaluating conceptual structure in cognitive science. Building from an existing human-generated dataset, we show that machine-verified norms capture aspects of conceptual structure beyond what is expressed in human norms alone, and better explain human judgments of semantic similarity amongst items that are distally related. The results suggest that LLMs can greatly enhance traditional methods of semantic feature norm verification, with implications for our understanding of conceptual representation in humans and machines.

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。

↑