2023
RoBoCoP: A Comprehensive ROmance BOrrowing COgnate Package and Benchmark for Multilingual Cognate Identification
Liviu P Dinu, Ana Sabina Uban, Alina Maria Cristea, Anca Daniela Dinu, Ioan-Bogdan Iordache, Simona Georgescu +1
EMNLP 2023long main
The identification of cognates is a fundamental process in historical linguistics, on which any further research is based. Even though there are several cognate databases for Romance languages, they are rather scattered, incomplete, noisy, contain unreliable information, or have uncertain availabili…