Myanmar ABSA - Aspect Detection Model (Stage 1)

A multi-label classification model for detecting aspects in Burmese product/service reviews. This is Stage 1 of a two-stage Aspect-Based Sentiment Analysis (ABSA) pipeline.

Model Details

  • Base Model: xlm-roberta-base
  • Architecture: XLM-RoBERTa for Sequence Classification
  • Problem Type: Multi-label classification
  • Language: Burmese (Myanmar)
  • License: MIT

Aspects Detected

The model predicts the presence of up to 5 aspects in a given review:

  1. product_quality - Quality, functionality, and effectiveness of products/services
  2. fulfillment_and_speed - Delivery speed, order fulfillment, and logistics
  3. price_and_value - Pricing, value for money, and cost-related aspects
  4. staff_and_service - Customer service, staff behavior, and support interactions
  5. variety_and_availability - Product variety, stock availability, and selection

Training Data

  • Total Samples: 5,281 Burmese reviews
  • Data Split: Stratified train/val/test split
    • Train: 4,224 samples
    • Validation: 528 samples
    • Test: 529 samples
  • Label Distribution: Multi-label annotations (reviews can have multiple aspects)
  • Taxonomy: Updated 5-aspect taxonomy (removed digital_experience, renamed aspects for clarity)

Performance Metrics

Evaluated on the test set:

Metric Score
Macro F1 0.9314
Micro F1 0.9279

Training Configuration

  • Learning Rate: 2e-5
  • Batch Size: 8 (with gradient accumulation steps = 4, effective batch size = 32)
  • Epochs: 4
  • Max Sequence Length: 128 tokens
  • Optimizer: AdamW
  • Precision: bfloat16

Usage

Basic Usage with Pipeline

from transformers import pipeline

# Load the model
classifier = pipeline(
    "text-classification",
    model="Fixaro/myanmar-absa-aspect-detection",
    return_all_scores=True,
    function_to_apply="sigmoid"  # For multi-label classification
)

# Predict aspects
review = "แ€•แ€…แ€นแ€…แ€Šแ€บแ€ธแ€กแ€›แ€Šแ€บแ€กแ€žแ€ฝแ€ฑแ€ธแ€€ แ€€แ€ฑแ€ฌแ€„แ€บแ€ธแ€•แ€ผแ€ฎแ€ธ แ€•แ€ญแ€ฏแ€ทแ€แ€ฌแ€œแ€Šแ€บแ€ธ แ€™แ€ผแ€”แ€บแ€แ€šแ€บ"
results = classifier(review)

# Results will show scores for all 5 aspects
for result in results[0]:
    if result['score'] > 0.5:  # Threshold for multi-label
        print(f"{result['label']}: {result['score']:.4f}")

Advanced Usage with Tokenizer

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load model and tokenizer
model_name = "Fixaro/myanmar-absa-aspect-detection"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Prepare input
review = "แ€ˆแ€ฑแ€ธแ€œแ€Šแ€บแ€ธ แ€žแ€€แ€บแ€žแ€ฌแ€แ€šแ€บแŠ แ€แ€”แ€บแ€‘แ€™แ€บแ€ธแ€แ€ฝแ€ฑแ€€แ€œแ€Šแ€บแ€ธ แ€–แ€ฑแ€ฌแ€บแ€›แ€ฝแ€ฑแ€แ€šแ€บ"
inputs = tokenizer(
    review,
    return_tensors="pt",
    truncation=True,
    max_length=128,
    padding=True
)

# Get predictions
with torch.no_grad():
    outputs = model(**inputs)
    logits = outputs.logits
    probabilities = torch.sigmoid(logits)
    
# Apply threshold (0.5)
threshold = 0.5
predictions = (probabilities > threshold).int()

# Map to aspect names
aspect_names = [
    "product_quality",
    "fulfillment_and_speed", 
    "price_and_value",
    "staff_and_service",
    "variety_and_availability"
]

detected_aspects = [
    aspect_names[i] 
    for i, pred in enumerate(predictions[0]) 
    if pred == 1
]

print(f"Detected aspects: {detected_aspects}")

Model Architecture

XLM-RoBERTa Base (xlm-roberta-base)
โ”œโ”€โ”€ Encoder: 12 transformer layers
โ”œโ”€โ”€ Hidden size: 768
โ”œโ”€โ”€ Attention heads: 12
โ””โ”€โ”€ Classification head: Linear(768, 5) with sigmoid activation

Limitations and Biases

  • Domain Specificity: Trained on product/service reviews; may not generalize to other domains
  • Language Limitation: Optimized for Burmese; performance may vary for code-mixed text
  • Aspect Overlap: Some reviews may express multiple aspects ambiguously
  • Threshold Sensitivity: The 0.5 threshold for multi-label prediction may need adjustment based on use case

Intended Use

This model is intended for:

  • Aspect detection in Burmese customer reviews
  • First stage of ABSA pipelines
  • Research and academic purposes
  • Commercial applications with proper validation

Citation

If you use this model in your research, please cite:

@software{myanmar_absa_aspect_detection,
  title = {Myanmar ABSA: Aspect Detection Model},
  author = {Fixaro},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/Fixaro/myanmar-absa-aspect-detection}
}

Related Models

Contact

For questions or issues, please open an issue on the model repository.

Downloads last month
3
Safetensors
Model size
0.3B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support