arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.00469cs.CLcs.AI
收藏

使意义的词:学习的词性表示中的感觉运动规范

Words that make SENSE: Sensorimotor Norms in Learned Lexical Token Representations

University of Southern California(南加州大学)

Abhinav Gupta, Toben H. Mintz, Jesse Thomason

AI总结:

本文提出SENSE模型,通过词嵌入预测Lancaster感觉运动规范,并通过行为研究验证了人类选择与SENSE评分之间的显著相关性。

摘要:

虽然词嵌入通过共现模式获取意义,但人类语言理解基于感觉和运动经验。我们提出了SENSE(Sensorimotor Embedding Norm Scoring Engine),一种学习投影模型,可从词词性嵌入预测Lancaster感觉运动规范。我们还进行了一项行为研究,281名参与者选择了候选非词中哪些能引发特定感觉运动关联,发现人类选择率与SENSE评分在11种模态中的6种上存在统计显著相关性。对这些非词选择率的子词分析揭示了内脏规范的系统音素特征,表明从文本数据中计算候选音素特征的路径。

英文摘要:

While word embeddings derive meaning from co-occurrence patterns, human language understanding is grounded in sensory and motor experience. We present $\text{SENSE}$ $(\textbf{S}\text{ensorimotor }$ $\textbf{E}\text{mbedding }$ $\textbf{N}\text{orm }$ $\textbf{S}\text{coring }$ $\textbf{E}\text{ngine})$, a learned projection model that predicts Lancaster sensorimotor norms from word lexical embeddings. We also conducted a behavioral study where 281 participants selected which among candidate nonce words evoked specific sensorimotor associations, finding statistically significant correlations between human selection rates and $\text{SENSE}$ ratings across 6 of the 11 modalities. Sublexical analysis of these nonce words selection rates revealed systematic phonosthemic patterns for the interoceptive norm, suggesting a path towards computationally proposing candidate phonosthemes from text data.

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。

↑