m-e5-small-vlsp2018-hotel

Overview

Vietnamese aspect-category sentiment classification model for hotel reviews from the VLSP 2018 sentiment analysis benchmark.

Model Details

• Base model: intfloat/multilingual-e5-small
• Architecture: absa
• Checkpoint source: vlsp-2018-hotel-e5-small-best.pt
• Sequence length used during training/inference pipeline: 256
• Number of aspect categories: 34

Label Schema

• 0: aspect not mentioned
• 1: positive
• 2: negative
• 3: neutral

Aspect Categories

• FACILITIES#CLEANLINESS
• FACILITIES#COMFORT
• FACILITIES#DESIGN&FEATURES
• FACILITIES#GENERAL
• FACILITIES#MISCELLANEOUS
• FACILITIES#PRICES
• FACILITIES#QUALITY
• FOOD&DRINKS#MISCELLANEOUS
• FOOD&DRINKS#PRICES
• FOOD&DRINKS#QUALITY
• FOOD&DRINKS#STYLE&OPTIONS
• HOTEL#CLEANLINESS
• HOTEL#COMFORT
• HOTEL#DESIGN&FEATURES
• HOTEL#GENERAL
• HOTEL#MISCELLANEOUS
• HOTEL#PRICES
• HOTEL#QUALITY
• LOCATION#GENERAL
• ROOMS#CLEANLINESS
• ROOMS#COMFORT
• ROOMS#DESIGN&FEATURES
• ROOMS#GENERAL
• ROOMS#MISCELLANEOUS
• ROOMS#PRICES
• ROOMS#QUALITY
• ROOM_AMENITIES#CLEANLINESS
• ROOM_AMENITIES#COMFORT
• ROOM_AMENITIES#DESIGN&FEATURES
• ROOM_AMENITIES#GENERAL
• ROOM_AMENITIES#MISCELLANEOUS
• ROOM_AMENITIES#PRICES
• ROOM_AMENITIES#QUALITY
• SERVICE#GENERAL

Dataset

• Dataset: VLSP 2018 Hotel Reviews This model is trained on the hotel subset of the VLSP 2018 aspect-based sentiment analysis benchmark.

Data Format

• Review is the input text column.
• Each aspect-category column is encoded as 0/1/2/3 for none, positive, negative, or neutral.

Splits

• Train: 3000 samples
• Validation: 2000 samples
• Test: 600 samples

Checkpoint Metrics

• loss: 0.2058
• accuracy: 0.9387

Usage

Load the model with trust_remote_code=True because this repository contains custom modeling code.

from transformers import AutoModelForSequenceClassification, AutoTokenizer

repo_id = "NeoCyber/m-e5-small-vlsp2018-hotel"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForSequenceClassification.from_pretrained(
    repo_id,
    trust_remote_code=True,
)

texts = ["Khách sạn sạch sẽ và nhân viên rất nhiệt tình."]
inputs = tokenizer(texts, return_tensors="pt", truncation=True, padding=True)
outputs = model(**inputs)
predictions = model.decode_predictions(outputs.logits)
print(predictions)

Notes

• The repository includes custom configuration_*.py and modeling_*.py files required by transformers AutoClasses.
• outputs.logits has shape [batch_size, num_aspects, 4] and model.decode_predictions(...) maps logits back to aspect-level labels.