Word-Centered Semantic Graphs for Interpretable Diachronic Sense Tracking
This provides an interpretable method for linguists and NLP researchers to analyze word sense evolution without predefined inventories, though it is incremental as it builds on existing embedding and language model techniques.
The researchers tackled the problem of tracking semantic shift in diachronic corpora by proposing a graph-based framework that integrates distributional similarity and lexical substitutability, and demonstrated its effectiveness on New York Times Magazine articles from 1980-2017 by capturing contrasting trajectories like sense replacement in 'trump' and gradual shifts in 'post'.
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.