Subword-Based Comparative Linguistics across 242 Languages Using Wikipedia Glottosets

TL;DR

This study introduces a large-scale, subword-based framework for cross-linguistic comparison of 242 languages using Wikipedia lexicons, revealing significant correlations between subword similarity and linguistic relatedness.

Contribution

It presents a novel framework utilizing Byte-Pair Encoding and rank-based subword vectors for scalable, quantitative comparison of lexical similarities across many languages.

Findings

BPE segmentation aligns with morpheme boundaries 95% better than random.

BPE vocabulary similarity correlates with genetic language relatedness (Mantel r=0.329).

Nearly half of cross-linguistic homographs have different segmentations, varying with phylogenetic distance.

Abstract

We present a large-scale comparative study of 242 Latin and Cyrillic-script languages using subword-based methodologies. By constructing 'glottosets' from Wikipedia lexicons, we introduce a framework for simultaneous cross-linguistic comparison via Byte-Pair Encoding (BPE). Our approach utilizes rank-based subword vectors to analyze vocabulary overlap, lexical divergence, and language similarity at scale. Evaluations demonstrate that BPE segmentation aligns with morpheme boundaries 95% better than random baseline across 15 languages (F1 = 0.34 vs 0.15). BPE vocabulary similarity correlates significantly with genetic language relatedness (Mantel r = 0.329, p < 0.001), with Romance languages forming the tightest cluster (mean distance 0.51) and cross-family pairs showing clear separation (0.82). Analysis of 26,939 cross-linguistic homographs reveals that 48.7% receive different segmentations across related languages, with variation correlating to phylogenetic distance. Our results provide quantitative macro-linguistic insights into lexical patterns across typologically diverse languages within a unified analytical framework.