pahri/setfit-indo-resto-RM-ibu-imas-polarity

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:

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
• Classification head: a LogisticRegression instance
• spaCy Model: id_core_news_trf
• SetFitABSA Aspect Model: pahri/setfit-indo-resto-RM-ibu-imas-aspect
• SetFitABSA Polarity Model: pahri/setfit-indo-resto-RM-ibu-imas-polarity
• Maximum Sequence Length: 8192 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
positive	'air krispi dan ayam bakar:Warung Sunda murah meriah dan makanannya enak. Favorit selada air krispi dan ayam bakar' 'Ayam bakar,sambel leunca:Ayam bakar,sambel leunca sambel terasi merah enak banget 9/10, perkedel jagung 8/10 makan pakai sambel mantap. Makan berdua sekitar 77k' ',sambel leunca sambel terasi merah enak banget 9:Ayam bakar,sambel leunca sambel terasi merah enak banget 9/10, perkedel jagung 8/10 makan pakai sambel mantap. Makan berdua sekitar 77k'
negative	', minus di menu tidak di cantumkan:Makanan biasa saja, minus di menu tidak di cantumkan harga. Posi nasi standar, kelebihan sambal sudah disediakan di mangkok. ' 'lebih diatur kah antriannya, kayanya pakai:It wasnt bad food at all. Tapi please mungkin bisa lebih diatur kah antriannya, kayanya pakai waiting list gak sesulit itu deh.' 'rasanya standar. Harga bisa dibilang murah:Tahu tempe perkedel rasanya standar. Harga bisa dibilang murah. Kalau yang masih penasaran ya boleh dateng coba tapi menurut saya overall biasa saja, tidak nemu wah nya dimana..'

Evaluation

Metrics

Label	Accuracy
all	0.8636

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(
    "pahri/setfit-indo-resto-RM-ibu-imas-aspect",
    "pahri/setfit-indo-resto-RM-ibu-imas-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	35.3922	90

Label	Training Sample Count
konflik	0
negatif	0
netral	0
positif	0

Training Hyperparameters

• batch_size: (6, 6)
• 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: True
• warmup_proportion: 0.1
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0036	1	0.2676	-
0.1799	50	0.0064	-
0.3597	100	0.0015	-
0.5396	150	0.0007	-
0.7194	200	0.0005	-
0.8993	250	0.0006	-

Framework Versions

• Python: 3.10.13
• SetFit: 1.0.3
• Sentence Transformers: 2.7.0
• spaCy: 3.7.4
• Transformers: 4.36.2
• 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}
}