Say hi to NorBERT!
In joint work, SANT and NLPL/EOSC-Nordic have trained and released the first large-scale transformer-based language model for Norwegian: NorBERT!
NorLM is a new initiative to develop Norwegian Large-scale Language Models. It represents a collaborative effort between the SANT project, NLPL (the Nordic Language Processing Laboratory) and EOSC-Nordic (a branch of the European Open Science Cloud).
We are now happy to announce the public release of the first-large scale Norwegian version of BERT – a transformer-based language model architecture found to greatly boost the performance for a range of NLP tasks. In addition to this NorBERT model, we have also released two Norwegian versions of the ELMo architecture, and additional LM variants will follow in the future.
For more details, please see the NorLM webpages: http://norlm.nlpl.eu