README.md

---
license: apache-2.0
language:
  - vi
base_model: vinai/phobert-base
library_name: transformers
pipeline_tag: token-classification
tags:
  - ner
  - vietnamese
  - address-parsing
  - phobert
metrics:
  - precision
  - recall
  - f1
model-index:
  - name: bert_all
    results:
      - task:
          type: token-classification
          name: Vietnamese Address NER
        metrics:
          - type: f1
            value: 0.8212719298245614
          - type: precision
            value: 0.7741602067183463
          - type: recall
            value: 0.8744892002335085
---

# bert_all

Fine-tuned PhoBERT for **Vietnamese address Named Entity Recognition**.
Extracts structured fields from free-form Vietnamese addresses (place name,
house number, street, ward, district, city).

**Source artefact**: `bert_all`
**Base model**: `vinai/phobert-base`
**Trained on**: Vietnamese address corpus (mixed sources)
**Saved at**: `2026-06-06T12:29:40.098669+00:00`

## Metrics

| Metric    | Value     |
|-----------|-----------|
| Precision | **0.7742** |
| Recall    | **0.8745** |
| F1        | **0.8213** |

## Labels

- `<PAD>`
- `B-CITY`
- `B-DISTRICT`
- `B-HOUSE_NUMBER`
- `B-PLACE_NAME`
- `B-STREET`
- `B-WARD`
- `I-CITY`
- `I-DISTRICT`
- `I-HOUSE_NUMBER`
- `I-PLACE_NAME`
- `I-STREET`
- `I-WARD`
- `O`

## Quickstart

```python
from transformers import pipeline

ner = pipeline("token-classification", model="open-thienhang-com/bert_all", aggregation_strategy="simple")
ner("123 Nguyễn Huệ, Phường Bến Nghé, Quận 1, TP Hồ Chí Minh")
# → [
#     {'entity_group': 'HOUSE_NUMBER', 'word': '123', ...},
#     {'entity_group': 'STREET',        'word': 'Nguyễn Huệ', ...},
#     {'entity_group': 'WARD',          'word': 'Phường Bến Nghé', ...},
#     {'entity_group': 'DISTRICT',      'word': 'Quận 1', ...},
#     {'entity_group': 'CITY',          'word': 'TP Hồ Chí Minh', ...},
#   ]
```

Or manual:

```python
from transformers import AutoTokenizer, AutoModelForTokenClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("open-thienhang-com/bert_all")
model = AutoModelForTokenClassification.from_pretrained("open-thienhang-com/bert_all").eval()

inputs = tokenizer("123 Nguyễn Huệ, Phường Bến Nghé, Quận 1, TP HCM",
                   return_tensors="pt", truncation=True, max_length=256)
with torch.no_grad():
    out = model(**inputs).logits
pred_ids = out.argmax(-1)[0].tolist()
labels = [model.config.id2label[i] for i in pred_ids]
tokens = tokenizer.convert_ids_to_tokens(inputs.input_ids[0])
for t, l in zip(tokens, labels):
    if l != "O" and l != "<PAD>":
        print(f"  {t:20s} → {l}")
```

## Limitations

- Trained on Vietnamese addresses ONLY — won't generalise to free-form Vietnamese text or addresses from other countries.
- Uses syllable-level input (no `vncorenlp` word segmentation required).
- Class imbalance: `PLACE_NAME` is the rarest label, so its precision is lower than CITY / WARD.

## Citation

If you use this model, please credit the base model and dataset sources:

```bibtex
@misc{phobert,
  title  = {PhoBERT: Pre-trained language models for Vietnamese},
  author = {Dat Quoc Nguyen and Anh Tuan Nguyen},
  year   = {2020}
}
```