SetFit Polarity Model with sentence-transformers/paraphrase-multilingual-mpnet-base-v2
This is a SetFit model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses sentence-transformers/paraphrase-multilingual-mpnet-base-v2 as the Sentence Transformer embedding model. A SetFitHead instance is used for classification. In particular, this model is in charge of classifying aspect polarities.
The model has been trained using an efficient few-shot learning technique that involves:
- Fine-tuning a Sentence Transformer with contrastive learning.
- Training a classification head with features from the fine-tuned Sentence Transformer.
This model was trained within the context of a larger system for ABSA, which looks like so:
- Use a spaCy model to select possible aspect span candidates.
- Use a SetFit model to filter these possible aspect span candidates.
- Use this SetFit model to classify the filtered aspect span candidates.
Model Details
Model Description
- Model Type: SetFit
- Sentence Transformer body: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
- Classification head: a SetFitHead instance
- spaCy Model: it_core_news_lg
- SetFitABSA Aspect Model: setfit-absa-aspect
- SetFitABSA Polarity Model: MattiaTintori/Final_polarity_Colab_It
- Maximum Sequence Length: 128 tokens
- Number of Classes: 3 classes
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Model Labels
Label | Examples |
---|---|
1 |
|
0 |
|
2 |
|
Evaluation
Metrics
Label | F1 |
---|---|
all | 0.8415 |
Uses
Direct Use for Inference
First install the SetFit library:
pip install setfit
Then you can load this model and run inference.
from setfit import AbsaModel
# Download from the 🤗 Hub
model = AbsaModel.from_pretrained(
"setfit-absa-aspect",
"MattiaTintori/Final_polarity_Colab_It",
)
# Run inference
preds = model("The food was great, but the venue is just way too busy.")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 14 | 42.1222 | 146 |
Label | Training Sample Count |
---|---|
0 | 914 |
1 | 345 |
2 | 148 |
Training Hyperparameters
- batch_size: (128, 32)
- num_epochs: (5, 32)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 10
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 0.04
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: True
- warmup_proportion: 0.1
- l2_weight: 0.02
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: True
Training Results
Epoch | Step | Training Loss | Validation Loss |
---|---|---|---|
0.0045 | 1 | 0.2501 | - |
0.0455 | 10 | 0.2514 | 0.2407 |
0.0909 | 20 | 0.2359 | 0.2252 |
0.1364 | 30 | 0.21 | 0.2067 |
0.1818 | 40 | 0.1984 | 0.1779 |
0.2273 | 50 | 0.1408 | 0.1469 |
0.2727 | 60 | 0.1246 | 0.1493 |
0.3182 | 70 | 0.0654 | 0.1312 |
0.3636 | 80 | 0.0546 | 0.1293 |
0.4091 | 90 | 0.0651 | 0.1222 |
0.4545 | 100 | 0.0374 | 0.1385 |
0.5 | 110 | 0.0546 | 0.1214 |
0.5455 | 120 | 0.0453 | 0.1284 |
0.5909 | 130 | 0.0269 | 0.1241 |
0.6364 | 140 | 0.0303 | 0.1451 |
0.6818 | 150 | 0.0355 | 0.1299 |
0.7273 | 160 | 0.0096 | 0.1329 |
0.7727 | 170 | 0.0129 | 0.1411 |
0.8182 | 180 | 0.0127 | 0.1325 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 3.1.0
- spaCy: 3.7.6
- Transformers: 4.39.0
- PyTorch: 2.4.0+cu121
- Datasets: 3.0.0
- Tokenizers: 0.15.2
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}
}
- Downloads last month
- 7
Inference API (serverless) has been turned off for this model.