Riyosha/setfit-absa-paraphrase-mpnet-base-v2-MovieReviews-aspect_1

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: /private/var/folders/d9/1xz8vq817d3_x9b35qzvvgjc0000gn/T/tmpdqdxo7tx/Riyosha/setfit-absa-paraphrase-mpnet-base-v2-MovieReviews-aspect_1
• SetFitABSA Polarity Model: setfit-absa-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	'score:Accompanied by an amazing score and STELLAR cinematography, the opening scene perfectly sets you in a mood that simply compels you to not miss a single second of the film, as the story unfolds before your eyes' 'story:Accompanied by an amazing score and STELLAR cinematography, the opening scene perfectly sets you in a mood that simply compels you to not miss a single second of the film, as the story unfolds before your eyes' 'directed:Superbly directed by Masaki Kobayashi, masterful performance from Tatsuya Nakadai, stunning cinematography from Yoshio Miyajima, and an affecting score composed by Toru Takemitsu – all some of the best at what they did.'
no aspect	'STELLAR cinematography:Accompanied by an amazing score and STELLAR cinematography, the opening scene perfectly sets you in a mood that simply compels you to not miss a single second of the film, as the story unfolds before your eyes' 'scene:Accompanied by an amazing score and STELLAR cinematography, the opening scene perfectly sets you in a mood that simply compels you to not miss a single second of the film, as the story unfolds before your eyes' 'mood:Accompanied by an amazing score and STELLAR cinematography, the opening scene perfectly sets you in a mood that simply compels you to not miss a single second of the film, as the story unfolds before your eyes'

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(
    "/private/var/folders/d9/1xz8vq817d3_x9b35qzvvgjc0000gn/T/tmpdqdxo7tx/Riyosha/setfit-absa-paraphrase-mpnet-base-v2-MovieReviews-aspect_1",
    "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	8	30.25	51

Label	Training Sample Count
no aspect	50
aspect	30

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
• l2_weight: 0.01
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0046	1	0.358	-
0.2294	50	0.2605	-
0.4587	100	0.1679	-
0.6881	150	0.0263	-
0.9174	200	0.0174	-

Framework Versions

• Python: 3.9.6
• SetFit: 1.1.1
• Sentence Transformers: 3.4.1
• spaCy: 3.7.5
• Transformers: 4.48.3
• PyTorch: 2.6.0
• Datasets: 3.3.0
• Tokenizers: 0.21.0

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}
}