Harnessing Deep Cross-lingual Word Embeddings to Infer Accurate Phylogenetic Trees

Abstract

Establishing language relatedness by inferring phylogenetic trees has been a topic of interest in the area of diachronic linguistics. However, existing methods face meaning conflation deficiency due to the usage of lexical similarity-based measures. In this paper, we utilize fourteen linked Indian Wordnets to create inter-language distances using our novel approach to compute 'language distances'. Our pilot study uses deep cross-lingual word embeddings to compute inter-language distances and provide an effective distance matrix to infer phylogenetic trees. We also develop a baseline method using lexical similarity-based metrics for comparison and identify that our approach produces better phylogenetic trees which club related languages closer when compared to the baseline approach.