Saved in:
Bibliographic Details
Main Authors: Kaipeng, Liu, Ling, Wu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.00554
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.