Downloads · 30 days
13
10% of all-time downloads
mbert-armenian-participle-punct
AlbertHakobyan/mbert-armenian-participle-punct
mbert-armenian-participle-punct is a token classification model from AlbertHakobyan. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
Fine-tuned bert-base-multilingual-cased that restores punctuation around Eastern Armenian participle clauses, framed as 4-class token labeling. From the CODASSCA 2026 paper Sequence Labeling for Low-Resource Syntax: A…
All-time downloads
132
Public
Parameters
177M
3.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.5 GB · 78%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026
- SHA
- 21f0d859
Base models
Model card
From the Hugging Face model README
mBERT — Armenian Participle-Clause Punctuation
Fine-tuned bert-base-multilingual-cased that restores punctuation around
Eastern Armenian participle clauses, framed as 4-class token labeling.
From the CODASSCA 2026 paper Sequence Labeling for Low-Resource Syntax:
Automatic Punctuation of Armenian Participle Clauses.
Labels
0 O · 1 COMMA_AFTER · 2 BUTH_AFTER · 3 REMOVE_COMMA
Results (macro-F1)
| Benchmark | macro-F1 |
|---|---|
| Gold 2K (noisy web text) | 0.4655 |
| Shtemaran 292 (clean textbook) | 0.5190 |
Training: 15% negative under-sampling of the majority O class; lower 6 layers
frozen; hyper-parameters tuned with Optuna (21 trials). See artifacts/ for the
raw checkpoint, best config, trial log and final results; training/ holds the notebook.
Usage
from transformers import AutoTokenizer, AutoModelForTokenClassification
tok = AutoTokenizer.from_pretrained("AlbertHakobyan/mbert-armenian-participle-punct")
model = AutoModelForTokenClassification.from_pretrained("AlbertHakobyan/mbert-armenian-participle-punct")
Ensemble
Best results come from a soft-vote of this model with the BiLSTM at alpha=0.45:
P = 0.45 * P_bilstm + 0.55 * P_mbert (macro-F1 0.6745 on Shtemaran). See the
bilstm-armenian-participle-punct repo.
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Languages
- hy
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026