najwaa/absa-laptops-polarity-p2

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:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. 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:

1. Use a spaCy model to select possible aspect span candidates.
2. Use a SetFit model to filter these possible aspect span candidates.
3. 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: setfit-absa-aspect
• SetFitABSA Polarity Model: najwaa/absa-laptops-polarity-p2
• Maximum Sequence Length: 384 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
positive	'computer is so light weight and easy to:this computer is so light weight and easy to carry.' 'and easy to carry.:this computer is so light weight and easy to carry.' 'very lightweight.:very lightweight.'
negative	"it's surprisingly heavy for daily commuting:The build quality feels premium but it's surprisingly heavy for daily commuting." ', though the keyboard feels cramped during:Fantastic display clarity and vibrant colors make this perfect for photo editing, though the keyboard feels cramped during long typing sessions.' ', but the screen brightness is disappointing in:The laptop boots up incredibly fast thanks to the SSD, but the screen brightness is disappointing in outdoor conditions.'
negative	'Screen could be better:Screen could be better' 'not worth the price value.:definitely not worth the price value.'

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",
    "najwaa/absa-laptops-polarity-p2",
)
# 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	3	21.4335	57

Label	Training Sample Count
negative	117
negative	2
positive	144

Training Hyperparameters

• batch_size: (32, 32)
• 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
• l2_weight: 0.01
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0009	1	0.2501	-
0.0092	10	-	0.2944
0.0184	20	-	0.2864
0.0276	30	-	0.2742
0.0368	40	-	0.2594
0.0460	50	0.2663	0.2441
0.0552	60	-	0.2303
0.0645	70	-	0.2173
0.0737	80	-	0.2003
0.0829	90	-	0.1756
0.0921	100	0.2106	0.1360
0.1013	110	-	0.0920
0.1105	120	-	0.0590
0.1197	130	-	0.0449
0.1289	140	-	0.0405
0.1381	150	0.0714	0.0308
0.1473	160	-	0.0255
0.1565	170	-	0.0349
0.1657	180	-	0.0311
0.1750	190	-	0.0258
0.1842	200	0.0129	0.0257
0.1934	210	-	0.0286

Framework Versions

• Python: 3.11.12
• SetFit: 1.1.2
• Sentence Transformers: 4.1.0
• spaCy: 3.7.5
• Transformers: 4.51.3
• PyTorch: 2.6.0+cu124
• Datasets: 3.6.0
• Tokenizers: 0.21.1

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}
}