--- library_name: setfit tags: - setfit - absa - sentence-transformers - text-classification - generated_from_setfit_trainer metrics: - accuracy widget: - text: nihh, buat bumbu masih kurang berani:Kemaren kebetulan makan babat sama nyobain cumi, buat tekstur babatnya itu engga alot sama sekali dan tidak amis, sedangkan buat cumi utuh lumayan gede juga tekstur kenyel kenyelnya dapet dan mateng juga sampe ke dalem. Tapi ada tapinyaa nihh, buat bumbu masih kurang berani dan kurang meresap. - text: servicenya😊..Menunya variatif, delicious:Baru pertama kali coba baby dutch pancake..Overall sukaa dengan food, place & servicenya😊..Menunya variatif, delicious, penyajian cepat & pelayanan sangat baik. - text: enak, tapi porsinya kecil untuk harganya:Makanannya enak, tapi porsinya kecil untuk harganya. Suasana bagus, tetapi layanannya lambat. - text: specialist itu. Varian minumnya juga cuma sedikit:Menunya gak banyak, pancake dan rosti aja. Karena specialist itu. Varian minumnya juga cuma sedikit. - text: enak. Favorit selada air krispi dan ayam bakar:Warung Sunda murah meriah dan makanannya enak. Favorit selada air krispi dan ayam bakar. Bakwan dan perkedelnya juga enak. Paru gorengnya lembut. Tak lengkap kalau kebandung. Kalau tidak makan siang disini pipeline_tag: text-classification inference: false --- # SetFit Polarity Model This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) 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](https://www.sbert.net) 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](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance - **spaCy Model:** id_core_news_trf - **SetFitABSA Aspect Model:** [pahri/setfit-indo-restomix-aspect](https://huggingface.co/pahri/setfit-indo-restomix-aspect) - **SetFitABSA Polarity Model:** [pahri/setfit-indo-restomix-polarity](https://huggingface.co/pahri/setfit-indo-restomix-polarity) - **Maximum Sequence Length:** 8192 tokens - **Number of Classes:** 2 classes ### Model Sources - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit) - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055) - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit) ### Model Labels | Label | Examples | |:---------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | negative | | | positive | | ## Uses ### Direct Use for Inference First install the SetFit library: ```bash pip install setfit ``` Then you can load this model and run inference. ```python from setfit import AbsaModel # Download from the 🤗 Hub model = AbsaModel.from_pretrained( "pahri/setfit-indo-restomix-aspect", "pahri/setfit-indo-restomix-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 | 28.3207 | 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 | |:------:|:----:|:-------------:|:---------------:| | 0.0003 | 1 | 0.3326 | - | ### 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 ```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} } ```