KBLab
/

bert-base-swedish-cased-reallysimple-ner

Token Classification

sequence-tagger-model

Inference Endpoints

Model card Files Files and versions Community

robinq commited on Feb 15, 2022

Commit

2e0e293

•

1 Parent(s): f0d2f9a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ widget:
 ## Cased data
-This model is based on [KB-BERT](https://huggingface.co/KB/bert-base-swedish-cased) and was fine-tuned on the [SUC 3.1](https://huggingface.co/datasets/KBLab/suc3_1) corpus, using the _simple_ tags and cased data.
 For this model we used a variation of the data that did **not** use BIO-encoding to differentiate between the beginnings (B), and insides (I) of named entity tags.
 The model was trained on the training data only, with the best model chosen by its performance on the validation data.

 ## Cased data
+This model is based on [KB-BERT](https://huggingface.co/KB/bert-base-swedish-cased) and was fine-tuned on the [SUCX 3.0 - NER](https://huggingface.co/datasets/KBLab/sucx3_ner) corpus, using the _simple_ tags and cased data.
 For this model we used a variation of the data that did **not** use BIO-encoding to differentiate between the beginnings (B), and insides (I) of named entity tags.
 The model was trained on the training data only, with the best model chosen by its performance on the validation data.