|
--- |
|
language: |
|
- hr |
|
- bs |
|
- sr |
|
- cnr |
|
- hbs |
|
|
|
- text: "Zovem se Marko i živim u Zagrebu. Radim u Beogradu na Filozofskom fakultetu." |
|
- license: apache-2.0 |
|
--- |
|
|
|
# The [BERTić](https://huggingface.co/CLASSLA/bcms-bertic)* [bert-ich] /bɜrtitʃ/ model fine-tuned for the task of named entity recognition in Bosnian, Croatian, Montenegrin and Serbian (BCMS) |
|
|
|
* The name should resemble the facts (1) that the model was trained in Zagreb, Croatia, where diminutives ending in -ić (as in fotić, smajlić, hengić etc.) are very popular, and (2) that most surnames in the countries where these languages are spoken end in -ić (with diminutive etymology as well). |
|
|
|
This is a fine-tuned version of the [BERTić](https://huggingface.co/CLASSLA/bcms-bertic) model on the following datasets: |
|
|
|
- the [hr500k](http://hdl.handle.net/11356/1183) dataset, 500 thousand tokens in size, standard Croatian |
|
- the [SETimes.SR](http://hdl.handle.net/11356/1200) dataset, 87 thousand tokens in size, standard Serbian |
|
- the [ReLDI-hr](http://hdl.handle.net/11356/1241) dataset, 89 thousand tokens in size, Internet (Twitter) Croatian |
|
- the [ReLDI-sr](http://hdl.handle.net/11356/1240) dataset, 92 thousand tokens in size, Internet (Twitter) Serbian |
|
|
|
The data was augmented with missing diacritics and standard data was additionally over-represented. The F1 obtained on dev data (train and test was merged into train) is 91.38. For a more detailed per-dataset evaluation of the BERTić model on the NER task have a look at the [main model page](https://huggingface.co/CLASSLA/bcms-bertic). |
