NazmusAshrafi/mams-ds-setfit-MiniLM-mpnet-absa-tesla-tweet-polarity

SetFit Polarity Model with sentence-transformers/paraphrase-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-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/paraphrase-mpnet-base-v2
• Classification head: a LogisticRegression instance
• spaCy Model: en_core_web_lg
• SetFitABSA Aspect Model: NazmusAshrafi/mams-ds-setfit-MiniLM-mpnet-absa-tesla-tweet-aspect
• SetFitABSA Polarity Model: NazmusAshrafi/mams-ds-setfit-MiniLM-mpnet-absa-tesla-tweet-polarity
• Maximum Sequence Length: 512 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	"best sit down food I've had:It might be the best sit down food I've had in the area, so if you are going to the upright citizen brigade, or the garden, it could be just the place for you." 'generous and the staff brings out multiple:Portions are fairly generous and the staff brings out multiple little bites and treats throughout dinner.' 'casual Middle Eastern menu looks familar,:The Food The casual Middle Eastern menu looks familar, but the food--made to order in the open kitchen--is a notch above its peers.'
neutral	"be just the place for you.:It might be the best sit down food I've had in the area, so if you are going to the upright citizen brigade, or the garden, it could be just the place for you." ') other food is served in:) other food is served in too-small portions, but at least it leaves room for dessert.' "room while the food on other peoples:Upon entering, I was impressed by the room while the food on other peoples' tables seemed enticing."
negative	'Though the service might be a:Though the service might be a little slow, the waitresses are very friendly.' 'was expecting poor service and ambience but:After reading other reviews I was expecting poor service and ambience but was pleasantly surprised by our more than helpful waiter.' 'we found the food to be so:Came recommended to us, but we found the food to be so-so, the service good, but we were told we could not order desert since the table we were at had a reservation waiting.'

Evaluation

Metrics

Label	Accuracy
all	0.4516

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(
    "NazmusAshrafi/mams-ds-setfit-MiniLM-mpnet-absa-tesla-tweet-aspect",
    "NazmusAshrafi/mams-ds-setfit-MiniLM-mpnet-absa-tesla-tweet-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	17	28.6364	53

Label	Training Sample Count
negative	10
neutral	12
positive	11

Training Hyperparameters

• batch_size: (16, 2)
• num_epochs: (1, 16)
• 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: False
• warmup_proportion: 0.1
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0217	1	0.2212	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 2.4.0
• spaCy: 3.7.4
• Transformers: 4.37.2
• PyTorch: 2.1.0+cu121
• Datasets: 2.17.1
• 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}
}