Setfit Absa Bge Small En V1.5 Restaurants Aspect

🚀 SetFit Aspect Model with BAAI/bge-small-en-v1.5 on SemEval 2014 Task 4 (Restaurants)

This SetFit model, trained on the SemEval 2014 Task 4 (Restaurants) dataset, is designed for Aspect Based Sentiment Analysis (ABSA). It uses BAAI/bge-small-en-v1.5 as the Sentence Transformer embedding model and a LogisticRegression instance for classification.

🚀 Quick Start

Installation

First, install the SetFit library:

pip install setfit

Inference

Then you can load this model and run inference.

from setfit import AbsaModel

# Download from the 🤗 Hub
model = AbsaModel.from_pretrained(
    "tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-aspect",
    "tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-polarity",
)
# Run inference
preds = model("The food was great, but the venue is just way too busy.")

✨ Features

• Efficient Few - Shot Learning: Trained using an efficient few - shot learning technique that combines fine - tuning a Sentence Transformer with contrastive learning and training a classification head with features from the fine - tuned model.
• Integrated into ABSA System: Plays a crucial role in a larger ABSA system by filtering possible aspect span candidates.

📚 Documentation

Model Details

Model Description

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Model Labels

Evaluation

Metrics

Training Details

Training Set Metrics

Training Hyperparameters

• batch_size: (256, 256)
• num_epochs: (5, 5)
• max_steps: 5000
• sampling_strategy: oversampling
• body_learning_rate: (2e-05, 1e-05)
• head_learning_rate: 0.01
• loss: CosineSimilarityLoss
• distance_metric: cosine_distance
• margin: 0.25
• end_to_end: False
• use_amp: True
• warmup_proportion: 0.1
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: True

Training Results

• The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Carbon Emitted: 0.018 kg of CO2
• Hours Used: 0.303 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.9.16
• SetFit: 1.0.0.dev0
• Sentence Transformers: 2.2.2
• spaCy: 3.7.2
• Transformers: 4.29.0
• PyTorch: 1.13.1+cu117
• Datasets: 2.15.0
• Tokenizers: 0.13.3

📄 License

This model is licensed under the apache-2.0 license.

📚 Citation

BibTeX

@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}