Instructions to use Kansallisarkisto/finbert-ner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kansallisarkisto/finbert-ner with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Kansallisarkisto/finbert-ner")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Kansallisarkisto/finbert-ner") model = AutoModelForTokenClassification.from_pretrained("Kansallisarkisto/finbert-ner") - Notebooks
- Google Colab
- Kaggle
Add article link
Browse files
README.md
CHANGED
|
@@ -23,6 +23,9 @@ Since the latter dataset contains also sensitive data, it has not been made publ
|
|
| 23 |
|
| 24 |
An example of how the model can be used for named entity recognition is provided in this [Colab notebook](https://colab.research.google.com/drive/1-koUCwz4aU_UvyZxSW-Awwf5RQftFk5m).
|
| 25 |
|
|
|
|
|
|
|
|
|
|
| 26 |
## Intended uses & limitations
|
| 27 |
|
| 28 |
The model has been trained to recognize the following named entities from a text in Finnish:
|
|
|
|
| 23 |
|
| 24 |
An example of how the model can be used for named entity recognition is provided in this [Colab notebook](https://colab.research.google.com/drive/1-koUCwz4aU_UvyZxSW-Awwf5RQftFk5m).
|
| 25 |
|
| 26 |
+
Motivations behind model development and the data selection and annotation processes have been described in more detail in the article [Making sense of bureaucratic documents – Named entity
|
| 27 |
+
recognition for state authority archives](https://library.imaging.org/archiving/articles/21/1/2).
|
| 28 |
+
|
| 29 |
## Intended uses & limitations
|
| 30 |
|
| 31 |
The model has been trained to recognize the following named entities from a text in Finnish:
|