omymble/setfit-absa-books-polarity

SetFit Polarity Model with sentence-transformers/all-MiniLM-L6-v2

This is a SetFit model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses sentence-transformers/all-MiniLM-L6-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/all-MiniLM-L6-v2
• Classification head: a LogisticRegression instance
• spaCy Model: en_core_web_lg
• SetFitABSA Aspect Model: omymble/setfit-absa-books-aspect
• SetFitABSA Polarity Model: omymble/setfit-absa-books-polarity
• Maximum Sequence Length: 256 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	'30 novels, Poirot had been a:After reading nearly 30 novels, Poirot had been a part of life' 'sweeping story by Michael Dobbs of political maneuvering:The cast of characters in this sweeping story by Michael Dobbs of political maneuvering, skullduggery, and backstabbing is an historical Who's Who of the times: the ailing, haughty, and pacifist Chamberlain, who personifies England's bitter memories of the Great War and the popular concept of "never again"; the ambitious and self-absorbed Churchill, whose pugnacity sometimes clouds prudence; the defeatist, philandering, and anti-Semitic U' ', the "key" and ":When he recovers, the "key" and " A Compleat Atlas of The House" are still there'
positive	"Jack is a wonderful:Jack is a wonderful beleaguered hero who starts off by quickly realizing he don't know jack even about himself and as he investigates realizes each new clue proves he knows even less than he thought" 'is a detailed biography of Alphonse Capone:This is a detailed biography of Alphonse Capone' 'to an undercover assignment:Carol is offered the bone of a possible promotion if she would agree to an undercover assignment'
negative	'making the entire killer plot read like an:The emotional connection between Hill and the killers in the two previous books is missing here, making the entire killer plot read like an afterthought' 'felt the whole story was pointless:In the end, I felt the whole story was pointless' 'Diabola becomes mad and:Diabola becomes mad and uses her powers to make their eyes sting'

Evaluation

Metrics

Label	Accuracy
all	0.7143

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(
    "omymble/setfit-absa-books-aspect",
    "omymble/setfit-absa-books-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	9	30.2105	84

Label	Training Sample Count
negative	6
neutral	42
positive	9

Training Hyperparameters

• batch_size: (256, 256)
• num_epochs: (2, 2)
• 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: True
• warmup_proportion: 0.1
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.125	1	0.3786	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 3.0.1
• spaCy: 3.7.4
• Transformers: 4.39.0
• PyTorch: 2.3.1+cu121
• Datasets: 2.20.0
• 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}
}