Hugging Face's logo

stefan-it
/
hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
0c07409
•
1 Parent(s): 37e4d1b

readme: add initial version of model card

Browse files

Hey,

this commit adds the initial version of model card.

Files changed (1) hide show
  1. README.md +74 -0
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: fr
3
+ license: mit
4
+ tags:
5
+ - flair
6
+ - token-classification
7
+ - sequence-tagger-model
8
+ base_model: dbmdz/bert-base-historic-multilingual-64k-td-cased
9
+ widget:
10
+ - text: Le Moniteur universel fait ressortir les avantages de la situation de l '
11
+ Allemagne , sa force militaire , le peu d ' intérêts personnels qu ' elle peut
12
+ avoir dans la question d ' Orient .
13
+ ---
14
+
15
+ # Fine-tuned Flair Model on French NewsEye NER Dataset (HIPE-2022)
16
+
17
+ This Flair model was fine-tuned on the
18
+ [French NewsEye](https://github.com/hipe-eval/HIPE-2022-data/blob/main/documentation/README-newseye.md)
19
+ NER Dataset using hmBERT 64k as backbone LM.
20
+
21
+ The NewsEye dataset is comprised of diachronic historical newspaper material published between 1850 and 1950
22
+ in French, German, Finnish, and Swedish.
23
+ More information can be found [here](https://dl.acm.org/doi/abs/10.1145/3404835.3463255).
24
+
25
+ The following NEs were annotated: `PER`, `LOC`, `ORG` and `HumanProd`.
26
+
27
+ # Results
28
+
29
+ We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration:
30
+
31
+ * Batch Sizes: `[4, 8]`
32
+ * Learning Rates: `[3e-05, 5e-05]`
33
+
34
+ And report micro F1-score on development set:
35
+
36
+ | Configuration | Seed 1 | Seed 2 | Seed 3 | Seed 4 | Seed 5 | Average |
37
+ |-------------------|--------------|--------------|--------------|------------------|--------------|-----------------|
38
+ | `bs8-e10-lr3e-05` | [0.8121][1] | [0.8147][2] | [0.8062][3] | [0.8037][4] | [0.8081][5] | 0.809 ± 0.0044 |
39
+ | `bs8-e10-lr5e-05` | [0.796][6] | [0.8116][7] | [0.8064][8] | [0.8008][9] | [0.8091][10] | 0.8048 ± 0.0063 |
40
+ | `bs4-e10-lr3e-05` | [0.7997][11] | [0.8043][12] | [0.7919][13] | [0.8089][14] | [0.8104][15] | 0.803 ± 0.0075 |
41
+ | `bs4-e10-lr5e-05` | [0.8065][16] | [0.8033][17] | [0.7974][18] | [**0.7285**][19] | [0.7949][20] | 0.7861 ± 0.0325 |
42
+
43
+ [1]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
44
+ [2]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
45
+ [3]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
46
+ [4]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
47
+ [5]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
48
+ [6]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
49
+ [7]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
50
+ [8]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
51
+ [9]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
52
+ [10]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
53
+ [11]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
54
+ [12]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
55
+ [13]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
56
+ [14]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
57
+ [15]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
58
+ [16]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
59
+ [17]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
60
+ [18]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
61
+ [19]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
62
+ [20]: https://hf.co/stefan-it/hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
63
+
64
+ The [training log](training.log) and TensorBoard logs (not available for hmBERT Base model) are also uploaded to the model hub.
65
+
66
+ More information about fine-tuning can be found [here](https://github.com/stefan-it/hmBench).
67
+
68
+ # Acknowledgements
69
+
70
+ We thank [Luisa März](https://github.com/LuisaMaerz), [Katharina Schmid](https://github.com/schmika) and
71
+ [Erion Çano](https://github.com/erionc) for their fruitful discussions about Historic Language Models.
72
+
73
+ Research supported with Cloud TPUs from Google's [TPU Research Cloud](https://sites.research.google/trc/about/) (TRC).
74
+ Many Thanks for providing access to the TPUs ❤️