This is a domain-adapted transformer-based language model for German-speaking job advertisements.
Is is based on
deepset/gbert-base, and adapted to the domain of job advertisements trough continued in-domain pretraining on 4 million German-speaking job ads from Switzerland 1990-2020 (5.9 GB data).
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (cc-by-nc-sa-4.0)
1@inproceedings{
2 title = "Evaluation of Transfer Learning and Domain Adaptation for Analyzing German-Speaking Job Advertisements",
3 author = "Gnehm, Ann-Sophie and
4 Bühlmann, Eva and
5 Clematide, Simon",
6 booktitle = "Proceedings of the 13th Language Resources and Evaluation Conference",
7 month = june,
8 year = "2022",
9 address = "Marseille, France",
10 publisher = "European Language Resources Association",
11}
You can use the model for masked language modeling, but it's intended to be fine-tuned on a downstream task.
The model is trained on German-Speaking job ads from Switzerland. It inherits potential bias of its base model, and may contain biases and stereotypes common in job advertisements.
The
Swiss Job Market Monitor aims at systematically expanding scientific knowledge about the job market and improving labour market transparency by informing the general public about current developments on the job market.
