Journaux-LM
The Journaux-LM is a language model pretrained on historical French newspapers. Technically the model itself is an ELECTRA model, which was pretrained with the TEAMS approach.
Datasets
Version 1 of the Journaux-LM was pretrained on the following publicly available datasets:
In total, the pretraining corpus has a size of 408GB.
Benchmarks (Named Entity Recognition)
We compare our Zeitungs-LM directly to the French Europeana BERT model (as Zeitungs-LM is supposed to be the successor of it) on various downstream tasks from the hmBench repository, which is focussed on Named Entity Recognition.
We report averaged micro F1-Score over 5 runs with different seeds and use the best hyper-parameter configuration on the development set of each dataset to report the final test score.
Development Set
The results on the development set can be seen in the following table:
| Model \ Dataset | AjMC | ICDAR | LeTemps | NewsEye | HIPE-2020 | Avg. |
|---|---|---|---|---|---|---|
| Europeana BERT | 85.7 | 77.63 | 67.14 | 82.68 | 85.98 | 79.83 |
| Journaux-LM v1 | 86.25 | 78.51 | 67.76 | 84.07 | 88.17 | 80.95 |
Our Journaux-LM leads to a performance boost of 1.12% compared to the German Europeana BERT model.
Test Set
The final results on the test set can be seen here:
| Model \ Dataset | AjMC | ICDAR | LeTemps | NewsEye | HIPE-2020 | Avg. |
|---|---|---|---|---|---|---|
| Europeana BERT | 81.06 | 78.17 | 67.22 | 73.51 | 81.00 | 76.19 |
| Journaux-LM v1 | 83.41 | 77.73 | 67.11 | 74.48 | 83.14 | 77.17 |
Our Journaux-LM beats the French Europeana BERT model by 0.98%.
Changelog
- 02.11.2024: Initial version of the model. More details are coming very soon!
Acknowledgements
Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC). Many Thanks for providing access to the TPUs ❤️
Made from Bavarian Oberland with ❤️ and 🥨.