SetFit Polarity Model with sentence-transformers/all-mpnet-base-v2
This is a SetFit model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses sentence-transformers/all-mpnet-base-v2 as the Sentence Transformer embedding model. A LogisticRegression 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/all-mpnet-base-v2
- Classification head: a LogisticRegression instance
- spaCy Model: en_core_web_sm
- SetFitABSA Aspect Model: joshuasundance/setfit-absa-all-MiniLM-L6-v2-laptops-aspect
- SetFitABSA Polarity Model: joshuasundance/setfit-absa-all-mpnet-base-v2-laptops-polarity
- Maximum Sequence Length: 384 tokens
- Number of Classes: 4 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 |
---|---|
neutral |
|
positive |
|
negative |
|
conflict |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.7008 |
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(
"joshuasundance/setfit-absa-all-MiniLM-L6-v2-laptops-aspect",
"joshuasundance/setfit-absa-all-mpnet-base-v2-laptops-polarity",
spacy_model="en_core_web_sm",
)
# Run inference
preds = model("This laptop meets every expectation and Windows 7 is great!")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 25.5873 | 48 |
Label | Training Sample Count |
---|---|
conflict | 2 |
negative | 45 |
neutral | 30 |
positive | 49 |
Training Hyperparameters
- batch_size: (128, 128)
- num_epochs: (5, 5)
- max_steps: -1
- 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
Epoch | Step | Training Loss | Validation Loss |
---|---|---|---|
0.0120 | 1 | 0.2721 | - |
0.6024 | 50 | 0.0894 | 0.2059 |
1.2048 | 100 | 0.0014 | 0.2309 |
1.8072 | 150 | 0.0006 | 0.2359 |
2.4096 | 200 | 0.0005 | 0.2373 |
3.0120 | 250 | 0.0004 | 0.2364 |
3.6145 | 300 | 0.0003 | 0.2371 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.11.7
- SetFit: 1.0.3
- Sentence Transformers: 2.3.0
- spaCy: 3.7.2
- Transformers: 4.37.2
- PyTorch: 2.1.2+cu118
- Datasets: 2.16.1
- Tokenizers: 0.15.1
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
- 48
Inference API (serverless) has been turned off for this model.
Model tree for joshuasundance/setfit-absa-all-mpnet-base-v2-laptops-polarity
Base model
sentence-transformers/all-mpnet-base-v2Evaluation results
- Accuracy on tomaarsen/setfit-absa-semeval-laptopstest set self-reported0.701