Automated Cognate Detection as a Supervised Link Prediction Task with Cognate Transformer

V Akavarapu, A Bhattacharya - arXiv preprint arXiv:2402.02926, 2024 - arxiv.org
Identification of cognates across related languages is one of the primary problems in
historical linguistics. Automated cognate identification is helpful for several downstream …

Weakly-supervised Deep Cognate Detection Framework for Low-Resourced Languages Using Morphological Knowledge of Closely-Related Languages

K Goswami, P Rani, T Fransen, JP McCrae - arXiv preprint arXiv …, 2023 - arxiv.org
Exploiting cognates for transfer learning in under-resourced languages is an exciting
opportunity for language understanding tasks, including unsupervised machine translation …

Evolutionary Insights Into Language Change: Cognate Transformer and Phylogenetic Testing in Historical Linguistics

AV Mahesh - 2024 - search.proquest.com
Several central problems of historical linguistics, the study of language change, involve
strenuous manual labor whether in the case of identification of cognates, reconstruction of …

A new type of typology: improving the utility of linguistic typology in natural language processing via continuous data representations

E Baylor - 2023 - search.proquest.com
Data from linguistic typology has the potential to aid in the training of natural language
processing (NLP) models, especially for low-resource languages. This assumes, though …