|
--- |
|
license: cc-by-nc-sa-4.0 |
|
language: |
|
- de |
|
tags: |
|
- public participation |
|
- text-based geo-location |
|
- sequence labeling |
|
--- |
|
|
|
## Model Description |
|
|
|
**bert-base-german-cased_cimt-location** is a fine-tuned BERT model that is built to predict location phrases using the B(beginning, LABEL_2)-I(inside, LABEL_1)-O(outside, LABEL_0) label schema. |
|
|
|
Specifically, this model is a *bert-base-german-cased* that was fine-tuned on https://github.com/juliaromberg/cimt-geographic-location-dataset. |
|
|
|
## Background |
|
|
|
This work is based on research in the project CIMT, which investigates the chances and challenges of involving citizens in political decisions in the context of sustainable mobility transitions. (for more information, visit https://www.cimt-hhu.de/en/) |
|
|
|
## Details & Evaluation Results |
|
|
|
Can be found in the corresponding publication https://www.cimt-hhu.de/wp-content/uploads/2023/11/Padjman_Projektarbeitsbericht.pdf. |
|
|
|
## Usage |
|
```python |
|
from transformers import BertForTokenClassification, BertTokenizer |
|
tokenizer = BertTokenizer.from_pretrained("juliaromberg/bert-base-german-cased_cimt-location") |
|
model = BertForTokenClassification.from_pretrained("juliaromberg/bert-base-german-cased_cimt-location") |
|
``` |
|
|
|
## Citation |
|
https://www.cimt-hhu.de/wp-content/uploads/2023/11/Padjman_Projektarbeitsbericht.pdf |
