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: setfit-absa-aspect
SetFitABSA Polarity Model: najwaa/absa-headphones-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	'Amazing sound quality with deep bass:Amazing sound quality with deep bass that really makes music come alive.' 'quality with deep bass that really makes:Amazing sound quality with deep bass that really makes music come alive.' 'The audio is crystal clear:The audio is crystal clear but they become uncomfortable after wearing for more than an hour.'
negative	'but they become uncomfortable after wearing for:The audio is crystal clear but they become uncomfortable after wearing for more than an hour.' 'feels a bit tight on larger heads:Excellent noise cancellation blocks out distractions, though the fit feels a bit tight on larger heads.' ', but the audio quality is mediocre compared:The build feels sturdy and durable, but the audio quality is mediocre compared to the price point.'
negative	'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-headphones-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	6	21.3092	57

Label	Training Sample Count
negative	69
negative	1
positive	82

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
0.0027	1	0.2597	-
0.0275	10	-	0.2737
0.0549	20	-	0.2504
0.0824	30	-	0.2237
0.1099	40	-	0.1987
0.1374	50	0.2665	0.1561
0.1648	60	-	0.0780
0.1923	70	-	0.0272
0.2198	80	-	0.0142
0.2473	90	-	0.0055
0.2747	100	0.0748	0.0039
0.3022	110	-	0.0024
0.3297	120	-	0.0021
0.3571	130	-	0.0014
0.3846	140	-	0.0011
0.4121	150	0.0025	0.0009
0.4396	160	-	0.0007
0.4670	170	-	0.0007
0.4945	180	-	0.0009
0.5220	190	-	0.0010
0.5495	200	0.0009	0.0009
0.5769	210	-	0.0008

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-headphones-polarity-p2