EMBEDDIA/litlat-bert

LitLat BERT is a trilingual model, using xlm-roberta-base architecture, trained on Lithuanian, Latvian, and English corpora . Focusing on three languages, the model performs better than multilingual BERT, while still offering an option for cross-lingual knowledge transfer, which a monolingual model wouldn't . The report the results as a macro F1 score of 3 named entity classes shared in all three datasets: person, location, organization . The results are the results of the study using F1 scores of three named entity classes shared in three datasets . The study was published in Znotins and Barzdins, 2020,