metadata
library_name: setfit
tags:
- setfit
- absa
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget:
- text: >-
kurangi bintang karna developer pelit dapat gold:ku kurangi bintang karna
developer pelit dapat gold buat beli shop susah harus nunggu 6 jam untuk
energi terisi full itupun hanya 3 biji sangat tidak memuaskan walau game
cukup seru buat santai alangkah baiknya jika energy buat main di unlimit
saja atau di update percepat isi energi buat play nya dan kendala di
jaringan padahal sinyal wifi kencang tapi masih suka lag semoga cepat ada
update supercell
- text: >-
untuk grafik story dah bagus:untuk grafik story dah bagus cuman minus di
sistem gacha dan artefak di tambah game nya tidak ramah f2p jadi banyak
player yang kesusahan dalam mengumpulkan primogem itu doang sih
- text: >-
gamenya asik sayangnya sinyal tiba tiba down:gamenya asik sayangnya sinyal
tiba tiba down dan gk bisa login lagi
- text: >-
bertarung melawan musuh joystick sering ngebug gak:saat bertarung melawan
musuh joystick sering ngebug gak bisa di gerakin dan terkadang hanya jalan
lurus saja tolong diperbaiki
- text: >-
game ini 1 peti terbatas saya berharap:kekurangan game ini 1 peti terbatas
saya berharap ini diubah menjadi seperti clash royale karena koin di game
ini tidak bisa didapat setiap waktu kecuali top up 2 tier rank tolong di
tambah sistem rank karena sistem rank akan membuat banyak player bersaing
dan menambah keseruan karna ada tantangan seperti clash royale 3 sinyal
bug sinyal mendadak lemah dan gk bisa masuk pertandingan karena game ini
masih baru jadi wajar tapi tolong diperbaiki untuk kenyamanan pemain
pipeline_tag: text-classification
inference: false
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: Funnyworld1412/review_game_absa-aspect
- SetFitABSA Polarity Model: Funnyworld1412/review_game_absa-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 |
---|---|
Negative |
|
Positive |
|
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(
"Funnyworld1412/review_game_absa-aspect",
"Funnyworld1412/review_game_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 | 7 | 43.8444 | 96 |
Label | Training Sample Count |
---|---|
konflik | 0 |
negatif | 0 |
netral | 0 |
positif | 0 |
Training Hyperparameters
- batch_size: (4, 4)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 1
- 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 |
---|---|---|---|
0.0020 | 1 | 0.1121 | - |
0.1010 | 50 | 0.0306 | - |
0.2020 | 100 | 0.0186 | - |
0.3030 | 150 | 0.0862 | - |
0.4040 | 200 | 0.0089 | - |
0.5051 | 250 | 0.0037 | - |
0.6061 | 300 | 0.0027 | - |
0.7071 | 350 | 0.0154 | - |
0.8081 | 400 | 0.238 | - |
0.9091 | 450 | 0.0095 | - |
Framework Versions
- Python: 3.10.13
- SetFit: 1.0.3
- Sentence Transformers: 3.0.1
- spaCy: 3.7.5
- Transformers: 4.36.2
- PyTorch: 2.1.2
- 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}
}