MattiaTintori/ABSA_Aspect_EN

SetFit Aspect 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 SetFitHead 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:

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 this SetFit model to filter these possible aspect span candidates.
3. Use a 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 SetFitHead instance
• spaCy Model: en_core_web_trf
• SetFitABSA Aspect Model: MattiaTintori/Final_aspect_Colab
• SetFitABSA Polarity Model: setfit-absa-polarity
• Maximum Sequence Length: 384 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	'price:The price is reasonable although the service is poor.' 'service:The price is reasonable although the service is poor.' 'service:The place is so cool and the service is prompt and curtious.'
no aspect	'stomach:The food was delicious but do not come here on a empty stomach.' 'place:I grew up eating Dosa and have yet to find a place in NY to satisfy my taste buds.' 'NY:I grew up eating Dosa and have yet to find a place in NY to satisfy my taste buds.'

Evaluation

Metrics

Label	F1
all	0.9231

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(
    "MattiaTintori/Final_aspect_Colab",
    "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	3	19.4137	62

Label	Training Sample Count
no aspect	430
aspect	711

Training Hyperparameters

• batch_size: (64, 4)
• num_epochs: (5, 32)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 10
• body_learning_rate: (8e-05, 8e-05)
• head_learning_rate: 0.04
• 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
0.0028	1	0.2878	-
0.0560	20	0.2409	0.2515
0.1120	40	0.2291	0.2319
0.1681	60	0.1354	0.1835
0.2241	80	0.0654	0.1389
0.2801	100	0.0334	0.1818
0.3361	120	0.0535	0.1408
0.3922	140	0.014	0.1564
0.4482	160	0.0119	0.1453
0.5042	180	0.0158	0.1511
0.5602	200	0.0157	0.1393
0.6162	220	0.005	0.1536
0.6723	240	0.0002	0.1546
0.7283	260	0.0002	0.1673
0.7843	280	0.0004	0.1655

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 3.0.1
• spaCy: 3.7.6
• Transformers: 4.39.0
• PyTorch: 2.3.1+cu121
• Datasets: 2.21.0
• 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}
}