metadata

library_name: setfit
tags:
  - setfit
  - absa
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
base_model: sentence-transformers/paraphrase-mpnet-base-v2
metrics:
  - accuracy
widget:
  - text: >-
      Service is quite friendly:Service is quite friendly, not too special but
      not bad either.
  - text: >-
      Service was amazingly fast:Service was amazingly fast and efficient,
      making the visit very enjoyable.
  - text: >-
      Service is quite good:Service is quite good, not too special but not bad
      either.
pipeline_tag: text-classification
inference: false
model-index:
  - name: SetFit Polarity Model with sentence-transformers/paraphrase-mpnet-base-v2
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 1
            name: Accuracy

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:

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/paraphrase-mpnet-base-v2
Classification head: a LogisticRegression instance
spaCy Model: en_core_web_lg
SetFitABSA Aspect Model: models/en-setfit-absa-model-aspect
SetFitABSA Polarity Model: models/en-setfit-absa-model-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
Neutral	'Service is standard,:Service is standard, nothing extraordinary.' 'Service is quite fast:Service is quite fast and quite friendly.' 'Service that is quite:Service that is quite efficient but not friendly makes the dining experience neutral.'
Positive	'Service from the staff:Service from the staff is very friendly.' 'Service from the staff:Service from the staff is very fast and professional.' 'Service from the staff:Service from the staff is quite friendly and helpful.'
Negative	'Service is very slow:Service is very slow and not friendly at all.' 'Service is very slow:Service is very slow and inefficient.' 'Service is very slow:Service is very slow and unresponsive.'

Evaluation

Metrics

Label	Accuracy
all	1.0

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(
    "models/en-setfit-absa-model-aspect",
    "models/en-setfit-absa-model-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	11.1429	16

Label	Training Sample Count
Negative	3
Neutral	6
Positive	5

Training Hyperparameters

batch_size: (4, 4)
num_epochs: (1, 1)
max_steps: -1
sampling_strategy: oversampling
num_iterations: 20
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
0.0071	1	0.153	-
0.3571	50	0.0035	-
0.7143	100	0.001	-

Framework Versions

Python: 3.10.13
SetFit: 1.0.3
Sentence Transformers: 2.7.0
spaCy: 3.7.4
Transformers: 4.39.3
PyTorch: 2.1.2
Datasets: 2.18.0
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}
}