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

SetFit Aspect 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 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/paraphrase-mpnet-base-v2
• Classification head: a LogisticRegression instance
• spaCy Model: en_core_web_lg
• SetFitABSA Aspect Model: NazmusAshrafi/setfit-absa-sm-stock-tweet-aspect
• SetFitABSA Polarity Model: NazmusAshrafi/setfit-absa-sm-stock-tweet-polarity
• Maximum Sequence Length: 512 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	'staff:But the staff was so horrible to us.' '@WholeMarsBlog: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.' '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.'
no aspect	'Tesla delivery estimates:Tesla delivery estimates are at around 364k from the analysts.' 'analysts:Tesla delivery estimates are at around 364k from the analysts.' '@Tesla critics: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.'

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/setfit-absa-sm-stock-tweet-aspect",
    "NazmusAshrafi/setfit-absa-sm-stock-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	7	34.3860	54

Label	Training Sample Count
no aspect	93
aspect	21

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
0.0017	1	0.2658	-
0.0868	50	0.2171	-
0.1736	100	0.0649	-
0.2604	150	0.0259	-
0.3472	200	0.0802	-
0.4340	250	0.0425	-
0.5208	300	0.0258	-
0.6076	350	0.0435	-
0.6944	400	0.0793	-
0.7812	450	0.0072	-
0.8681	500	0.0003	-
0.9549	550	0.0116	-

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}
}