Bo-Boundary-mmBert

Bo-Boundary-mmBert

A ModernBERT model fine-tuned on Tibetan text for text-boundary detection (token classification). Each token is classified as either a boundary token (B) or a non-boundary token (O).

Model Details

Training

Data

The boundary label is extremely rare — B : O ratio is 1 : 638 — so negative window sampling (ratio 0.1) and focal loss were used to handle the class imbalance.

Hyperparameters

Infrastructure

• GPU: 1 × NVIDIA GeForce RTX 4090 (23.5 GB)
• Training time: ~24 h 52 min

Training Curve

The model was evaluated every 200 optimisation steps. Key milestones:

Best checkpoint selected by F2 score: 0.6510 at step 9,800 (epoch 5).

Evaluation on Benchmark

The best checkpoint was evaluated on 30 held-out benchmark documents with tolerance = 25 and threshold = 0.75.

Aggregate Metrics

Per-Document Highlights

The model performs best on clean sources (google_books, ocrv1) and can struggle on noisier OCR or pages with no true boundaries (false-positive predictions on zero-boundary pages).

Limitations

• The model was trained on a specific corpus of Tibetan texts; generalisation to unseen document styles or OCR engines may vary.
• High recall (0.854) but moderate precision (0.644) means the model tends to over-predict boundaries — downstream consumers should apply confidence thresholding.
• Pages with zero true boundaries can produce false-positive boundary predictions.

Credits

This model was trained by Dharmaduta from specifications provided by the Buddhist Digital Resource Center (BDRC) for the BDRC Etext Corpus, with funding from the Khyentse Foundation.