Towards a Map of Related Words in Romance Languages

Liviu P. Dinu, Ana Sabina Uban, Ioan-Bogdan Iordache, Claudia Vlad, Simona Georgescu, Laurentiu Zoicas, Anca Dinu


Abstract
We propose a map of cognates and borrowings usage in Romance languages, having as a starting point the pairs of cognates and borrowings between any two of these idioms from RoBoCoP, the largest database built upon electronic dictionaries containing etymological information for Portuguese, Spanish, French, Italian and Romanian. Having in mind that words are used and evolve in language communities over time, on the basis of the pairs extracted from RoBoCoP, we determine how many of them occur and with what frequency in the context of the languages in use, based on three online parallel corpora that contain all five Romance languages: Wikipedia, Europarl – focusing on proceedings of the European Parliament and RomCro2.0 – containing literary texts in different languages, translated in Romance languages and Croatian.
Anthology ID:
2025.ranlp-1.37
Volume:
Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Galia Angelova, Maria Kunilovskaya, Marie Escribe, Ruslan Mitkov
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
299–305
Language:
URL:
https://aclanthology.org/2025.ranlp-1.37/
DOI:
Bibkey:
Cite (ACL):
Liviu P. Dinu, Ana Sabina Uban, Ioan-Bogdan Iordache, Claudia Vlad, Simona Georgescu, Laurentiu Zoicas, and Anca Dinu. 2025. Towards a Map of Related Words in Romance Languages. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 299–305, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Towards a Map of Related Words in Romance Languages (Dinu et al., RANLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.ranlp-1.37.pdf