Cognate Identification to improve Phylogenetic trees for Indian Languages
Diptesh Kanojia, Malhar Kulkarni, Pushpak Bhattacharyya, Gholemreza Haffari · 2019
Cognates are present in multiple variants of the same text across different languages. Computational Phylogenetics uses algorithms and techniques to analyze these variants and infer phylogenetic trees for a hypothesized accurate representation based on the output of the computational algorithm used. In our work, we detect cognates among a few Indian languages namely Hindi, Marathi, Punjabi, and Sanskrit for helping build cognate sets for phylogenetic inference. Cognate detection helps phylogenetic inference by helping isolate diachronic sound changes and thus detect the words of a common origin. A cognate set manually annotated with the help of a lexicographer is generally used to automatically infer phylogenetic trees. Our work creates cognate sets of each language pair and infers phylogenetic trees based on a bayesian framework using the Maximum likelihood method.