Automated Cognate Detection as a Supervised Link Prediction Task with Cognate Transformer
This work addresses a key problem in historical linguistics for researchers, though it appears incremental as it builds on prior methods with a novel approach.
The paper tackles automated cognate detection across related languages by proposing a transformer-based architecture, which outperforms existing methods with increased supervision and reduces computation time while improving performance.
Identification of cognates across related languages is one of the primary problems in historical linguistics. Automated cognate identification is helpful for several downstream tasks including identifying sound correspondences, proto-language reconstruction, phylogenetic classification, etc. Previous state-of-the-art methods for cognate identification are mostly based on distributions of phonemes computed across multilingual wordlists and make little use of the cognacy labels that define links among cognate clusters. In this paper, we present a transformer-based architecture inspired by computational biology for the task of automated cognate detection. Beyond a certain amount of supervision, this method performs better than the existing methods, and shows steady improvement with further increase in supervision, thereby proving the efficacy of utilizing the labeled information. We also demonstrate that accepting multiple sequence alignments as input and having an end-to-end architecture with link prediction head saves much computation time while simultaneously yielding superior performance.