erikhenriksson commited on
Commit
96af35b
·
verified ·
1 Parent(s): 49aca8a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -103,7 +103,7 @@ tags:
103
  ---
104
  # Web register classification (multilingual model)
105
 
106
- A multilingual web register classifier, fine-tuned from XLM-RoBERTa-large.
107
  The model is trained with the multilingual CORE corpora across five languages (English, Finnish, French, Swedish, Turkish) to classify documents based on the [CORE taxonomy](https://turkunlp.org/register-annotation-docs/).
108
  It can predict labels for the 100 languages covered by XLM-RoBERTa-large. The model achieves state-of-the-art performance in classifying web registers for the trained languages and has strong transfer performance (see Evaluation below).
109
  It is designed to support the development of open language models and for linguists analyzing register variation.
 
103
  ---
104
  # Web register classification (multilingual model)
105
 
106
+ A multilingual web register classifier, fine-tuned from [XLM-RoBERTa-large](https://huggingface.co/FacebookAI/xlm-roberta-large).
107
  The model is trained with the multilingual CORE corpora across five languages (English, Finnish, French, Swedish, Turkish) to classify documents based on the [CORE taxonomy](https://turkunlp.org/register-annotation-docs/).
108
  It can predict labels for the 100 languages covered by XLM-RoBERTa-large. The model achieves state-of-the-art performance in classifying web registers for the trained languages and has strong transfer performance (see Evaluation below).
109
  It is designed to support the development of open language models and for linguists analyzing register variation.