Total runs:
16.1K
Run Growth:
7.3K
Growth Rate:
45.31%
Sponsored by
YouArt
dicta-il / MsBERT
Model's Last Updated: September 03 2024
fill-mask
Introduction of MsBERT
Model Details of MsBERT
MsBERT: A New Model for the Reconstruction of Lacunae in Hebrew Manuscripts
A new pretrained dedicated BERT model, dubbed MsBERT (short for: Manuscript BERT), designed from the ground up to handle Hebrew manuscript text. MsBERT substantially outperforms all existing Hebrew BERT models regarding the prediction of missing words in fragmentary Hebrew manuscript transcriptions in multiple genres, as well as regarding the task of differentiating between quoted passages and exegetical elaborations. We provide MsBERT for free download and unrestricted use, and we also provide an interactive and user-friendly website to allow manuscript scholars to leverage the power of MsBERT in their scholarly work of reconstructing fragmentary Hebrew manuscripts.
You can try out the website here: https://msbert.dicta.org.il .
Sample usage:
from transformers import AutoModelForMaskedLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('dicta-il/MsBERT')
model = AutoModelForMaskedLM.from_pretrained('dicta-il/MsBERT')
model.eval()
text = '''ויצפהו זהב [MASK] מרכבו ארגמן ר' [MASK] א' [MASK] פרוכת הסמוכה לה ר' ביבי א' זו [MASK] שזהבה דומה לארגמן'''
output = model(tokenizer.encode(text, return_tensors='pt'))
# the first [MASK] is the token #4 (including [CLS])
import torch
top_2 = torch.topk(output.logits[0, 4, :], 2)[1]
print('\n'.join(tokenizer.convert_ids_to_tokens(top_2))) # should print טהור / סגור
Citation
If you use MsBERT in your research, please cite
MsBERT: A New Model for the Reconstruction of Lacunae in Hebrew Manuscripts
BibTeX:
@inproceedings{msbert-2024,
title = "MsBERT: A New Model for the Reconstruction of Lacunae in Hebrew Manuscripts",
author = "Shmidman, Avi and Shmidman, Ometz and Gershuni, Hillel and Koppel, Moshe",
booktitle = "Proceedings of the 1st Machine Learning for Ancient Language Workshop (ML4AL 2024)",
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
}
License
Shield:
This work is licensed under a Creative Commons Attribution 4.0 International License .
Runs of dicta-il MsBERT on huggingface.co
96
Total runs
-65
24-hour runs
-138
3-day runs
-135
7-day runs
-298
30-day runs
More Information About MsBERT huggingface.co Model
Url of MsBERT
MsBERT huggingface.co Url
Provider of MsBERT huggingface.co
Other API from dicta-il
Updated:September 09 2026
Total runs:
15.6K
Run Growth:
13.0K
Growth Rate:
82.86%
Total runs:
14.3K
Run Growth:
8.9K
Growth Rate:
62.18%
Total runs:
12.4K
Run Growth:
7.9K
Growth Rate:
64.12%
Total runs:
6.1K
Run Growth:
2.3K
Growth Rate:
37.69%
Total runs:
5.4K
Run Growth:
2.2K
Growth Rate:
39.85%
Total runs:
4.4K
Run Growth:
2.6K
Growth Rate:
57.88%
Total runs:
4.3K
Run Growth:
-223
Growth Rate:
-5.18%
Total runs:
2.2K
Run Growth:
554
Growth Rate:
24.85%
Total runs:
2.1K
Run Growth:
585
Growth Rate:
28.44%
Total runs:
2.1K
Run Growth:
-1.2K
Growth Rate:
-57.33%
Total runs:
1.9K
Run Growth:
37
Growth Rate:
1.95%
Total runs:
1.5K
Run Growth:
-781
Growth Rate:
-51.62%
Total runs:
1.4K
Run Growth:
-1.4K
Growth Rate:
-99.29%
Total runs:
994
Run Growth:
99
Growth Rate:
9.96%
Total runs:
861
Run Growth:
39
Growth Rate:
5.35%
Total runs:
559
Run Growth:
-64
Growth Rate:
-11.45%
Total runs:
407
Run Growth:
-139
Growth Rate:
-34.15%
Total runs:
391
Run Growth:
34
Growth Rate:
8.70%
Total runs:
385
Run Growth:
-815
Growth Rate:
-211.69%
Total runs:
381
Run Growth:
296
Growth Rate:
77.69%
Total runs:
363
Run Growth:
-564
Growth Rate:
-155.37%
Total runs:
333
Run Growth:
-724
Growth Rate:
-217.42%
Total runs:
315
Run Growth:
288
Growth Rate:
91.43%
Total runs:
287
Run Growth:
157
Growth Rate:
54.70%
Total runs:
271
Run Growth:
-133
Growth Rate:
-49.08%
Total runs:
263
Run Growth:
-126
Growth Rate:
-47.91%
Total runs:
203
Run Growth:
-439
Growth Rate:
-216.26%
Total runs:
134
Run Growth:
0
Growth Rate:
0.00%
Total runs:
108
Run Growth:
-84
Growth Rate:
-77.78%
Total runs:
54
Run Growth:
-64
Growth Rate:
-118.52%
Total runs:
46
Run Growth:
-468
Growth Rate:
-1017.39%
Total runs:
44
Run Growth:
-72
Growth Rate:
-163.64%
Total runs:
39
Run Growth:
28
Growth Rate:
71.79%
Total runs:
38
Run Growth:
33
Growth Rate:
86.84%
Total runs:
34
Run Growth:
24
Growth Rate:
70.59%
Total runs:
26
Run Growth:
-124
Growth Rate:
-476.92%
Total runs:
23
Run Growth:
14
Growth Rate:
60.87%
Total runs:
17
Run Growth:
-3
Growth Rate:
-17.65%
Total runs:
17
Run Growth:
11
Growth Rate:
64.71%
Total runs:
16
Run Growth:
4
Growth Rate:
25.00%
Total runs:
14
Run Growth:
-4
Growth Rate:
-28.57%
Total runs:
12
Run Growth:
6
Growth Rate:
50.00%
Total runs:
11
Run Growth:
1
Growth Rate:
9.09%
Total runs:
8
Run Growth:
0
Growth Rate:
0.00%
Total runs:
8
Run Growth:
-1
Growth Rate:
-12.50%
Total runs:
5
Run Growth:
-7
Growth Rate:
-140.00%
Total runs:
4
Run Growth:
-2
Growth Rate:
-50.00%