A Hierarchical and Attentional Analysis of Argument Structure Constructions in BERT Using Naturalistic Corpora
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Dimensionality ReductionSimilar Papers 제목 키워드 기반
Event Structure Representation: Between Verbs and Argument Structure Constructions
This paper proposes a novel representation of event structure by separating verbal semantics and the meaning of argument structure constructions that verbs occur in. Our model demonstrates how the two meaning representat…
Predicting Japanese Word Order in Double Object Constructions
This paper presents a statistical model to predict Japanese word order in the double object constructions. We employed a Bayesian linear mixed model with manually annotated predicate-argument structure data. The findings…
ObjectRepresenting constructional metaphors
This paper introduces a representation and annotation scheme for argument structure constructions that are used metaphorically with verbs in different semantic domains. We aim to contribute to the study of constructional…
Neural reality of argument structure constructions
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 grammar…
SentenceHierarchical Multitask Learning with Dependency Parsing for Japanese Semantic Role Labeling Improves Performance of Argument Identification
With the advent of FrameNet and PropBank, many semantic role labeling (SRL) systems have been proposed in English. Although research on Japanese predicate argument structure analysis (PASA) has been conducted, most studi…
Dependency ParsingSemantic Role Labeling