21 citations · 40 across the 4 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.CL2021
Training dataset and dictionary sizes matter in BERT models: the case of Baltic languages
Matej Ulčar, Marko Robnik-Šikonja
Large pretrained masked language models have become state-of-the-art solutions for many NLP problems. While studies have shown that monolingual models produce better results than m…
cs.CL2021★ 6 cited
Evaluation of contextual embeddings on less-resourced languages
Matej Ulčar, Aleš Žagar, Carlos S. Armendariz +4
The current dominance of deep neural networks in natural language processing is based on contextual embeddings such as ELMo, BERT, and BERT derivatives. Most existing work focuses…