README.md

metadata

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

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:

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:

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