SetFit Polarity Model

This is a SetFit model that can be used for Aspect Based Sentiment Analysis (ABSA). 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
Classification head: a LogisticRegression instance
spaCy Model: id_core_news_trf
SetFitABSA Aspect Model: kaylaisya/absa-aspect
SetFitABSA Polarity Model: kaylaisya/absa-polarity
Maximum Sequence Length: 8192 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
positif	'enak enak, pelayanannya juga mantap,:makanannya enak enak, pelayanannya juga mantap, terbaik lah' 'Rasanya selalu enak gak:Rasanya selalu enak gak pernah berubah, higines. Anak2 pada suka makan ayam goreng mcd' 'Pelayanannya cukup ramah dan:Pelayanannya cukup ramah dan praktis. Makanannya enak dan segar, khususnya es krim. Sip, lah.'
netral	'nya unik.. harganya standar lah sesuai:Sangat strategis,ramai, cukup luas dan nyaman, pelayanan ramah dan cepat.. parkiran juga luas , akhirnya kesampaian juga cobain menu ayam gulai cukup enak&cita rasa nya unik.. harganya standar lah sesuai rasa ,salam sukses selalu ☺️' 'makan siang, tempat nya menjorok kedalam:Mampir ke sini bareng temen mau makan siang, tempat nya menjorok kedalam, tatanan design nya MCD semua standard sesuai dengan kapasitas lahan nya, tempatnya juga dijaga banget kebersihannya, pelayanannya bagus, kakak-kakak pelayannya juga …' 'mbanya bantu take tempat, gesit ketika:Ini mba2nya supuer helpfull, karena kesana serombongan ber10 orang, mbanya bantu take tempat, gesit ketika dimintai bantuan. …'
negatif	'Pelayanan DriveThru terburuk!:Pelayanan DriveThru terburuk!!! Parkiran jg sempit gak bs keluar kalo batal drive thru. Ngantri drive thru 1 jam! Gak abis pikir. Tolong deh diperbaiki. Jika memang gak bs melayani, kasi tau dan segera ditutup drpd orang menunggu lama. Tolong banget management McD buah batu diperhatikan' 'Apa-apaan ini pelayanannya, pesen coke:Apa-apaan ini pelayanannya, pesen coke float doang sampe 32 menit. Dah gitu tadi datang workernya bilang ga ready sodanya, lah aturan dari awal pas payment di kasir langsung ngomong kalo ada mulut & otak. Kek gitu lalu nyuruh aku konfir ke kasir, …' 'menu paket ,rasa ayam crispyny agak:Over all ok...\nCm kmriin pesen menu paket ,rasa ayam crispyny agak asin.. smga kedepan lebih baik lg.'

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(
    "kaylaisya/absa-aspect",
    "kaylaisya/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	6	27.2254	64

Label	Training Sample Count
konflik	0
negatif	12
netral	24
positif	758

Training Hyperparameters

batch_size: (64, 64)
num_epochs: (1, 1)
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: False

Framework Versions

Python: 3.10.12
SetFit: 1.0.3
Sentence Transformers: 3.0.1
spaCy: 3.7.4
Transformers: 4.36.2
PyTorch: 2.3.0+cu121
Datasets: 2.19.2
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}
}