SetFit Aspect Model with sentence-transformers/all-MiniLM-L6-v2

This is a SetFit model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses sentence-transformers/all-MiniLM-L6-v2 as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification. In particular, this model is in charge of filtering aspect span candidates.

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 this SetFit model to filter these possible aspect span candidates.
Use a SetFit model to classify the filtered aspect span candidates.

Model Details

Model Description

Model Type: SetFit
Sentence Transformer body: sentence-transformers/all-MiniLM-L6-v2
Classification head: a LogisticRegression instance
spaCy Model: en_core_web_sm
SetFitABSA Aspect Model: najwaa/absa-digital_cameras-aspect-p2
SetFitABSA Polarity Model: setfit-absa-polarity
Maximum Sequence Length: 256 tokens
Number of Classes: 2 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
aspect	'autofocus:The autofocus is lightning fast and the image quality is absolutely stunning for portraits.' 'image quality:The autofocus is lightning fast and the image quality is absolutely stunning for portraits.' 'auto focus:the images are sharp, the auto focus is easy to use, and the lens is decent quality.'
no aspect	'lightning:The autofocus is lightning fast and the image quality is absolutely stunning for portraits.' 'portraits:The autofocus is lightning fast and the image quality is absolutely stunning for portraits.' 'quality:the images are sharp, the auto focus is easy to use, and the lens is decent quality.'

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(
    "najwaa/absa-digital_cameras-aspect-p2",
    "setfit-absa-polarity",
)
# 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	4	18.1429	52

Label	Training Sample Count
no aspect	319
aspect	213

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
0.0002	1	0.2723	-
0.0022	10	-	0.3128
0.0043	20	-	0.3119
0.0065	30	-	0.3104
0.0087	40	-	0.3085
0.0108	50	0.3162	0.3060
0.0130	60	-	0.3032
0.0152	70	-	0.2996
0.0173	80	-	0.2956
0.0195	90	-	0.2917
0.0217	100	0.2978	0.2884
0.0238	110	-	0.2846
0.0260	120	-	0.2800
0.0282	130	-	0.2766
0.0303	140	-	0.2739
0.0325	150	0.2866	0.2704
0.0347	160	-	0.2672
0.0368	170	-	0.2648
0.0390	180	-	0.2630
0.0412	190	-	0.2619
0.0433	200	0.2731	0.2614
0.0455	210	-	0.2612
0.0477	220	-	0.2613
0.0498	230	-	0.2613
0.0520	240	-	0.2612
0.0542	250	0.2593	0.2612
0.0563	260	-	0.2611
0.0585	270	-	0.2611
0.0607	280	-	0.2611
0.0628	290	-	0.2612
0.0650	300	0.2616	0.2612
0.0672	310	-	0.2612

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}
}

najwaa
/

absa-digital_cameras-aspect-p2