基于自然语料的BERT中论证结构构建的层次化与注意力分析
A Hierarchical and Attentional Analysis of Argument Structure Constructions in BERT Using Naturalistic Corpora
AI总结:
本文通过分析BERT处理论证结构构建的方式,揭示了模型在不同层次中对信息的层次化表示和注意力机制的作用。
摘要:
本研究探讨了双向编码表示Transformer模型如何处理四种基本的论证结构构建。我们采用多维分析框架,整合MDS、t-SNE作为降维方法,Generalized Discrimination Value(GDV)作为聚类分离度量,Fisher Discriminant Ratio(FDR)作为线性诊断探测,以及注意力机制分析。我们的结果揭示出一种层次化的表示结构。构建特定信息在早期层中出现,在中层形成最大分离的聚类,并在后续处理阶段得以保持。
英文摘要:
This study investigates how the Bidirectional Encoder Representations from Transformers model processes four fundamental Argument Structure Constructions. We employ a multi-dimensional analytical framework, which integrates MDS, t-SNE as dimensionality reduction, Generalized Discrimination Value (GDV) as cluster separation metrics, Fisher Discriminant Ratio (FDR) as linear diagnostic probing, and attention mechanism analysis. Our results reveal a hierarchical representational structure. Construction-specific information emerges in early layers, forms maximally separable clusters in middle layers, and is maintained through later processing stages.
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。