|
--- |
|
license: cc-by-4.0 |
|
language: |
|
- da |
|
pipeline_tag: text-classification |
|
widget: |
|
- text: Rigtig god service! |
|
--- |
|
|
|
# What is this? |
|
|
|
BERT classification model for short customer reviews written in Danish. |
|
|
|
The model uses 5 classes ranging from 1-5 stars: |
|
|
|
* ⭐ (very poor) |
|
* ⭐⭐ (poor) |
|
* ⭐⭐⭐ (neutral) |
|
* ⭐⭐⭐⭐ (good) |
|
* ⭐⭐⭐⭐⭐ (very good) |
|
|
|
The model is fine-tuned using the pre-trained [Danish BERT model]("Maltehb/danish-bert-botxo"). |
|
|
|
# How to use |
|
|
|
Test the model using the [🤗Transformers](https://github.com/huggingface/transformers) library pipeline: |
|
|
|
```python |
|
from transformers import pipeline |
|
|
|
classifier = pipeline("sentiment-analysis", model="KennethTM/danish-bert-review-sentiment") |
|
classifier("Intet virkede og ingen hjælp at hente.") |
|
|
|
#[{'label': '⭐', 'score': 0.4953940808773041}] |
|
``` |
|
|
|
Or load it using the Auto* classes: |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification |
|
|
|
model = AutoModelForSequenceClassification.from_pretrained("KennethTM/danish-bert-review-sentiment") |
|
tokenizer = AutoTokenizer.from_pretrained("KennethTM/danish-bert-review-sentiment") |
|
``` |
|
|