|
--- |
|
tags: |
|
- spacy |
|
- token-classification |
|
language: |
|
- da |
|
license: apache-2.0 |
|
model-index: |
|
- name: da_dacy_medium_ner_fine_grained |
|
results: |
|
- task: |
|
name: NER |
|
type: token-classification |
|
metrics: |
|
- name: NER Precision |
|
type: precision |
|
value: 0.7937743191 |
|
- name: NER Recall |
|
type: recall |
|
value: 0.8176352705 |
|
- name: NER F Score |
|
type: f_score |
|
value: 0.8055281343 |
|
datasets: |
|
- chcaa/DANSK |
|
--- |
|
|
|
<a href="https://github.com/centre-for-humanities-computing/Dacy"><img src="https://centre-for-humanities-computing.github.io/DaCy/_static/icon.png" width="175" height="175" align="right" /></a> |
|
|
|
# DaCy_medium_ner_fine_grained |
|
|
|
DaCy is a Danish language processing framework with state-of-the-art pipelines as well as functionality for analyzing Danish pipelines. |
|
At the time of publishing this model, also included in DaCy encorporates the only models for fine-grained NER using DANSK dataset - a dataset containing 18 annotation types in the same format as Ontonotes. |
|
Moreover, DaCy's largest pipeline has achieved State-of-the-Art performance on Named entity recognition, part-of-speech tagging and dependency parsing for Danish on the DaNE dataset. |
|
Check out the [DaCy repository](https://github.com/centre-for-humanities-computing/DaCy) for material on how to use DaCy and reproduce the results. |
|
DaCy also contains guides on usage of the package as well as behavioural test for biases and robustness of Danish NLP pipelines. |
|
|
|
For information about the use of this model as well as guides to its use, please refer to [DaCys documentation](https://centre-for-humanities-computing.github.io/DaCy/using_dacy.html). |
|
|
|
| Feature | Description | |
|
| --- | --- | |
|
| **Name** | `da_dacy_medium_ner_fine_grained` | |
|
| **Version** | `0.1.0` | |
|
| **spaCy** | `>=3.5.0,<3.6.0` | |
|
| **Default Pipeline** | `transformer`, `ner` | |
|
| **Components** | `transformer`, `ner` | |
|
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) | |
|
| **Sources** | [DANSK - Danish Annotations for NLP Specific TasKs](https://huggingface.co/datasets/chcaa/DANSK) (chcaa)<br />[vesteinn/DanskBERT](https://huggingface.co/vesteinn/DanskBERT) (Vésteinn Snæbjarnarson) | |
|
| **License** | `apache-2.0` | |
|
| **Author** | [Centre for Humanities Computing Aarhus](https://chcaa.io/#/) | |
|
|
|
### Label Scheme |
|
|
|
<details> |
|
|
|
<summary>View label scheme (18 labels for 1 components)</summary> |
|
|
|
| Component | Labels | |
|
| --- | --- | |
|
| **`ner`** | `CARDINAL`, `DATE`, `EVENT`, `FACILITY`, `GPE`, `LANGUAGE`, `LAW`, `LOCATION`, `MONEY`, `NORP`, `ORDINAL`, `ORGANIZATION`, `PERCENT`, `PERSON`, `PRODUCT`, `QUANTITY`, `TIME`, `WORK OF ART` | |
|
|
|
</details> |
|
|
|
### Accuracy |
|
|
|
| Type | Score | |
|
| --- | --- | |
|
| `ENTS_F` | 80.55 | |
|
| `ENTS_P` | 79.38 | |
|
| `ENTS_R` | 81.76 | |
|
| `TRANSFORMER_LOSS` | 17272.76 | |
|
| `NER_LOSS` | 82090.19 | |
|
|
|
### Training |
|
|
|
For progression in loss and performance on the dev set during training, please refer to the Weights and Biases run, [HERE](https://wandb.ai/emil-tj/dacy-an-efficient-pipeline-for-danish/runs/eg0wvam7?workspace=user-emil-tj) |
