NazmusAshrafi/setfit-absa-sm-stock-tweet-sentiment

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: setfit-absa-aspect
• SetFitABSA Polarity Model: NazmusAshrafi/setfit-absa-sm-stock-tweet-sentiment
• Maximum Sequence Length: 512 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
negative	'But the staff was so horrible:But the staff was so horrible to us.' 'For years @WholeMarsBlog viciously silenced @Tesla:For years @WholeMarsBlog viciously silenced @Tesla critics. Failing to silence me, he desperately lashes out with childish insults about me, my company, my products - and even my His fear and impotence spurs me on to ensure that everyone understands Full Self-Driving is Apple.' "$NIO just because I:$NIO just because I'm down money doesn't mean this is a bad investment. The whole market, everything sucks right now. 2-5 years from now, I'm confident it will pay off."
neutral	'-Driving is Apple.:For years @WholeMarsBlog viciously silenced @Tesla critics. Failing to silence me, he desperately lashes out with childish insults about me, my company, my products - and even my His fear and impotence spurs me on to ensure that everyone understands Full Self-Driving is Apple.' "adopt California's rules approved in August:New York state plans to adopt California's rules approved in August that would require all new vehicles sold in the state by 2035 to be either electric or plug-in electric hybrids." "plug-in electric hybrids.:New York state plans to adopt California's rules approved in August that would require all new vehicles sold in the state by 2035 to be either electric or plug-in electric hybrids."
positive	'day! #Tesla #hawaii $:This makes my day! #Tesla #hawaii $TSLA' '@TeslaSolar roof stood up:@TeslaSolar roof stood up to #HurricaneIan with 155mph winds and storm surge! This Powerwall was underwater for hours and is still working perfectly.' 'surge! This Powerwall was underwater for:@TeslaSolar roof stood up to #HurricaneIan with 155mph winds and storm surge! This Powerwall was underwater for hours and is still working perfectly.'
neutral	'Investing in the stock market was and never:Investing in the stock market was and never will be easy bc many throw in the white towel along the way, bc they panic. '

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",
    "NazmusAshrafi/setfit-absa-sm-stock-tweet-sentiment",
)
# 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	10	33.3333	60

Label	Training Sample Count
negative	7
neutral	5
neutral	1
positive	8

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
0.0526	1	0.1621	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.2
• Sentence Transformers: 2.2.2
• spaCy: 3.6.1
• Transformers: 4.35.2
• PyTorch: 2.1.0+cu121
• Datasets: 2.16.1
• Tokenizers: 0.15.0

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}
}