From Dataset to Model: A Romanian–English Corpus and Fine-Tuned Cross-Lingual Embeddings for Text and Tabular Retrieval
Sign Up to like & getrecommendations! Published in 2025 at "Applied Sciences"
DOI: 10.3390/app152212219
Abstract: This study introduces a Romanian–English bilingual corpus and a fine-tuned cross-lingual embedding framework aimed at improving retrieval performance in Retrieval-Augmented Generation (RAG) systems. The dataset integrates over 130,000 unstructured question–answer pairs derived from SQuAD and… read more here.
Keywords: corpus fine; retrieval; tuned cross; fine tuned ... See more keywords