XLM-RoBERTa-large
A multilingual pre-trained encoder released by Meta AI, based on the RoBERTa architecture and trained on the CommonCrawl corpus covering 100 languages, with approximately 560 million parameters.
Timeline (last 90 days)
The jointly trained multilingual XLM-RoBERTa-large model achieved the best strict F1 on almost all languages and entity types, exceeding the strongest monolingual system by up to 0.13 F1.
XLM-RoBERTa-large is a multilingual pretrained encoder released by Facebook AI (now Meta AI), based on the RoBERTa architecture, trained on a CommonCrawl corpus covering 100 languages, with about 560 million parameters.
All Facts (2)
The jointly trained multilingual XLM-RoBERTa-large model achieved the best strict F1 on almost all languages and entity types, exceeding the strongest monolingual system by up to 0.13 F1.
50%UnverifiedXLM-RoBERTa-large is a multilingual pretrained encoder released by Facebook AI (now Meta AI), based on the RoBERTa architecture, trained on a CommonCrawl corpus covering 100 languages, with about 560 million parameters.
50%