Word-Centered Semantic Graphs for Interpretable Diachronic Sense Tracking

2026-01-29

AI Summary

This work proposes an interpretable, lexicon-free framework for tracking dynamic semantic change in diachronic corpora through word-centered semantic graphs. The approach integrates distributional similarity from diachronic Skip-gram embeddings with lexical substitutability derived from time-specific masked language models to construct target-word-centered semantic graphs. By applying graph clustering and cross-temporal node alignment, the method reveals polysemous structures and their evolutionary trajectories over time. Experiments on The New York Times Magazine corpus (1980–2017) demonstrate that the framework effectively captures diverse patterns of semantic evolution—including event-driven sense replacement, semantic stability, and gradual associative shifts—thereby significantly enhancing the granularity and interpretability of semantic change analysis.

Technology Category

• Natural Language Processing: Lexical Semantics and Morphology
• Data Mining & Knowledge Management: Semantic Web
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Models for Web evolution
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

We propose an interpretable, graph-based framework for analyzing semantic shift in diachronic corpora. For each target word and time slice, we induce a word-centered semantic network that integrates distributional similarity from diachronic Skip-gram embeddings with lexical substitutability from time-specific masked language models. We identify sense-related structure by clustering the peripheral graph, align clusters across time via node overlap, and track change through cluster composition and normalized cluster mass. In an application study on a corpus of New York Times Magazine articles (1980 - 2017), we show that graph connectivity reflects polysemy dynamics and that the induced communities capture contrasting trajectories: event-driven sense replacement (trump), semantic stability with cluster over-segmentation effects (god), and gradual association shifts tied to digital communication (post). Overall, word-centered semantic graphs offer a compact and transparent representation for exploring sense evolution without relying on predefined sense inventories.

Problem

• semantic shift
• diachronic sense tracking
• word meaning evolution
• polysemy dynamics
• interpretable representation

Innovation

• word-centered semantic graphs
• diachronic sense tracking
• distributional semantics
• lexical substitutability
• cluster alignment