Article citationsMore>>

Asgari, E., & Mofrad, M. R. K. (2016). Comparing Fifty Natural Languages and Twelve Genetic Languages Using Word Embedding Language Divergence (WELD) as a Quantitative Measure of Language Distance. In Proceedings of the Workshop on Multilingual and Cross-Lingual Methods in NLP (pp. 65-74). Association for Computational Linguistics.
https://doi.org/10.18653/v1/w16-1208

has been cited by the following article:

• TITLE: Quantifying Language Disparities: A Distance-Based Predictive Model Using Linguistic Tree Structures

  AUTHORS: Akshata Chavan, Nicole Lee, Rezza Moieni, Mary Legrand

  KEYWORDS: Linguistic Evolution, Language Disparity, Shortest Path Algorithms, Exponential Decay, Levenshtein Distance, Computational Linguistics, Quantitative Linguistics, Network Analysis

  JOURNAL NAME: Open Journal of Social Sciences, Vol.13 No.12, December 31, 2025

  ABSTRACT: Understanding the historical evolution and divergence of languages requires a quantitative framework for measuring their relationships. Traditional linguistic classifications provide hierarchical structures but lack numerical quantification of language disparity. This project addresses this gap by developing a computational model to quantify linguistic distance within a language tree. This study employs a graph-based model, utilising the Shortest Path Algorithm and Levenshtein Distance to determine the minimum distance between languages, capturing their ancestral and lexical relationships, respectively. This distance is then converted into a relationship score using an exponential decay function, reflecting the observed non-linear pattern of linguistic similarity. The resulting model provides a robust computational tool for understanding language disparity, moving beyond broad classifications to provide numerical insights into how closely languages are related, contributing to the study of language evolution.