tlemberger
commited on
Commit
•
6c42a83
1
Parent(s):
6bbac4f
so many typos
Browse files
README.md
CHANGED
@@ -18,7 +18,7 @@ metrics:
|
|
18 |
|
19 |
This model is a [RoBERTa base model](https://huggingface.co/roberta-base) that was further trained using a masked language modeling task on a compendium of english scientific textual examples from the life sciences using the [BioLang dataset](https://huggingface.co/datasets/EMBO/biolang). It was then fine-tuned for token classification on the SourceData [sd-figures](https://huggingface.co/datasets/EMBO/sd-figures) dataset with the `PANELIZATION` task to perform 'parsing' or 'segmentation' of figure legends into fragments corresponding to sub-panels.
|
20 |
|
21 |
-
Figures are usually composite representations of results obtained with
|
22 |
|
23 |
## Intended uses & limitations
|
24 |
|
@@ -44,15 +44,15 @@ The model must be used with the `roberta-base` tokenizer.
|
|
44 |
|
45 |
## Training data
|
46 |
|
47 |
-
The model was trained for token classification using the [EMBO/sd-figures
|
48 |
|
49 |
## Training procedure
|
50 |
|
51 |
-
The training was run on
|
52 |
|
53 |
Training code is available at https://github.com/source-data/soda-roberta
|
54 |
|
55 |
-
- Model fine-tuned:
|
56 |
- Tokenizer vocab size: 50265
|
57 |
- Training data: EMBO/sd-figures
|
58 |
- Dataset configuration: PANELIZATION
|
|
|
18 |
|
19 |
This model is a [RoBERTa base model](https://huggingface.co/roberta-base) that was further trained using a masked language modeling task on a compendium of english scientific textual examples from the life sciences using the [BioLang dataset](https://huggingface.co/datasets/EMBO/biolang). It was then fine-tuned for token classification on the SourceData [sd-figures](https://huggingface.co/datasets/EMBO/sd-figures) dataset with the `PANELIZATION` task to perform 'parsing' or 'segmentation' of figure legends into fragments corresponding to sub-panels.
|
20 |
|
21 |
+
Figures are usually composite representations of results obtained with heterogeneous experimental approaches and systems. Breaking figures into panels allows identifying more coherent descriptions of individual scientific experiments.
|
22 |
|
23 |
## Intended uses & limitations
|
24 |
|
|
|
44 |
|
45 |
## Training data
|
46 |
|
47 |
+
The model was trained for token classification using the [`EMBO/sd-figures PANELIZATION`](https://huggingface.co/datasets/EMBO/sd-figures) dataset which includes manually annotated examples.
|
48 |
|
49 |
## Training procedure
|
50 |
|
51 |
+
The training was run on an NVIDIA DGX Station with 4XTesla V100 GPUs.
|
52 |
|
53 |
Training code is available at https://github.com/source-data/soda-roberta
|
54 |
|
55 |
+
- Model fine-tuned: EMBO/bio-lm
|
56 |
- Tokenizer vocab size: 50265
|
57 |
- Training data: EMBO/sd-figures
|
58 |
- Dataset configuration: PANELIZATION
|