arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.12246cs.CL
收藏

论元结构建构的神经现实性

Neural reality of argument structure constructions

University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(向量人工智能研究所);Unity Health Toronto(多伦多团结健康医院)

Bai Li, Zining Zhu, Guillaume Thomas, Frank Rudzicz, Yang Xu

摘要:

在词汇主义语言学理论中,论元结构被认为是可以从动词的意义预测的。因此,动词是决定从句意义的主要因素。相反,构式语法学家认为论元结构编码在构式(或形式-意义对)中,与动词不同。几十年的心理语言学研究已经产生了大量的实证证据支持构式观点。在这里,我们采用一些心理语言学的研究,探讨存在的论点结构建设(ASC)的转换为基础的语言模型(LM)。首先,通过一个句子排序实验,我们发现,共享同一个结构的句子比共享同一个动词的句子在嵌入空间上更接近。此外,母语学习者越来越倾向于使用更多输入数据的结构进行分组,这反映了非母语学习者的行为。第二,在一个基于“Jabberwocky”启动的实验中,我们发现LM将ASC与意义联系起来,即使是在语义上无意义的句子中。我们的工作提供了第一个证据,ASCs在LM和突出的潜力,设计新颖的探测方法,在心理语言学研究的基础上。

英文摘要:

In lexicalist linguistic theories, argument structure is assumed to be predictable from the meaning of verbs. As a result, the verb is the primary determinant of the meaning of a clause. In contrast, construction grammarians propose that argument structure is encoded in constructions (or form-meaning pairs) that are distinct from verbs. Decades of psycholinguistic research have produced substantial empirical evidence in favor of the construction view. Here we adapt several psycholinguistic studies to probe for the existence of argument structure constructions (ASCs) in Transformer-based language models (LMs). First, using a sentence sorting experiment, we find that sentences sharing the same construction are closer in embedding space than sentences sharing the same verb. Furthermore, LMs increasingly prefer grouping by construction with more input data, mirroring the behaviour of non-native language learners. Second, in a "Jabberwocky" priming-based experiment, we find that LMs associate ASCs with meaning, even in semantically nonsensical sentences. Our work offers the first evidence for ASCs in LMs and highlights the potential to devise novel probing methods grounded in psycholinguistic research.

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。

↑