A model based on KB/bert-base-swedish-cased trained for CEFR level classification of learner essays.
Standard reference
Ricardo Muñoz Sánchez, David Alfter, Simon Dobnik, Maria Irena Szawerna, Elena Volodina
(2024):
Jingle BERT, Jingle BERT, Frozen All the Way: Freezing Layers to Identify CEFR Levels of Second Language Learners Using BERT,
in Proceedings of the 13th Workshop on Natural Language Processing for Computer Assisted Language Learning (NLP4CALL 2024),
pages 137-152
Data citation
Muñoz Sánchez, Ricardo. sbx/KB-bert-swedish_CEFR-classification [Data set]. Enriched and distributed by Språkbanken. https://doi.org/10.23695/hqj9-mx09
Additional ways to cite the dataset.
Caveats
This model is not meant to be used in high-stakes contexts. It is meant to be used exclusively as a language-learning tool.
Intended uses
CEFR level classification
Download
| File | Size | Modified | Licence |
|---|---|---|---|
|
KB-bert-swedish_CEFR-classification
The model is hosted on HuggingFace and can be easily accessed e.g. using their Python library.
|
122.87 KB | GPL-3.0 |