Subword-Based Comparative Linguistics across 242 Languages Using Wikipedia Glottosets
This work provides quantitative macro-linguistic insights for researchers in computational linguistics and comparative linguistics, though it is incremental as it applies existing methods to new data.
The study tackled the problem of large-scale cross-linguistic comparison by analyzing 242 Latin and Cyrillic-script languages using subword-based methods, resulting in findings such as BPE segmentation aligning with morpheme boundaries 95% better than a random baseline and BPE vocabulary similarity correlating with genetic relatedness (Mantel r = 0.329).
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.