--- base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2 library_name: setfit metrics: - f1 pipeline_tag: text-classification tags: - setfit - absa - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: Locale:Locale molto bene arredato, con stile e atmosfera tipica valtellinese. Cucina ottima, dal bastone di carne al pesce, dai pizzoccheri agli gnocchetti, dal vino ai dolci, tutto perfetto e soprattutto di grande qualità... Filippo poi è un’autentica forza della natura, molto simpatico, cordiale e amichevole,...Altro - text: cucina:Locale accogliente e familiare...bravissima la ragazza in cucina, come le ragazze al banco e in sala! CONSIGLIATO - text: servizio:Il servizio era impeccabile e il tortello di zucca era sublime. - text: cucina:Il ristorante propone piatti vegetariani che NON sono vegetariani. Dopo aver specificato al servizio la nostra etica alimentare, ci è stata consigliata una portata che durante la consumazione abbiamo constatato con amarezza che avesse parti di maiale come ingredienti (confermato dalla cucina). Poco valgono le...scuse del servizio, trovo assurdo e inconcepibile che situazioni del genere possano accadere nel 2024. Evidentemente questo è indice della poca professionalità di questo ristorante.Altro - text: servizio:La polenta con formaggio era saporita, ma il servizio è stato lento. inference: false model-index: - name: SetFit Aspect Model with sentence-transformers/paraphrase-multilingual-mpnet-base-v2 results: - task: type: text-classification name: Text Classification dataset: name: Unknown type: unknown split: test metrics: - type: f1 value: 0.8096514745308312 name: F1 --- # SetFit Aspect Model with sentence-transformers/paraphrase-multilingual-mpnet-base-v2 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) as the Sentence Transformer embedding model. A [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance is used for classification. In particular, this model is in charge of filtering aspect span candidates. 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 this SetFit model to filter these possible aspect span candidates.** 3. Use a SetFit model to classify the filtered aspect span candidates. ## Model Details ### Model Description - **Model Type:** SetFit - **Sentence Transformer body:** [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) - **Classification head:** a [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance - **spaCy Model:** it_core_news_lg - **SetFitABSA Aspect Model:** [MattiaTintori/Final_aspect_Colab_It](https://huggingface.co/MattiaTintori/Final_aspect_Colab_It) - **SetFitABSA Polarity Model:** [setfit-absa-polarity](https://huggingface.co/setfit-absa-polarity) - **Maximum Sequence Length:** 128 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 | |:----------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | aspect | | | no aspect | | ## Evaluation ### Metrics | Label | F1 | |:--------|:-------| | **all** | 0.8097 | ## 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( "MattiaTintori/Final_aspect_Colab_It", "setfit-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 | 9 | 40.3192 | 137 | | Label | Training Sample Count | |:----------|:----------------------| | no aspect | 1379 | | aspect | 1378 | ### Training Hyperparameters - batch_size: (128, 32) - num_epochs: (5, 32) - max_steps: -1 - sampling_strategy: oversampling - num_iterations: 10 - body_learning_rate: (5e-05, 5e-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 - l2_weight: 0.02 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: True ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:----------:|:-------:|:-------------:|:---------------:| | 0.0023 | 1 | 0.2484 | - | | 0.0464 | 20 | 0.2718 | 0.259 | | 0.0928 | 40 | 0.2581 | 0.2544 | | 0.1392 | 60 | 0.2266 | 0.2475 | | 0.1856 | 80 | 0.233 | 0.2298 | | 0.2320 | 100 | 0.2104 | 0.2145 | | **0.2784** | **120** | **0.1487** | **0.2106** | | 0.3248 | 140 | 0.1615 | 0.2314 | | 0.3712 | 160 | 0.1328 | 0.2164 | | 0.4176 | 180 | 0.0905 | 0.2164 | | 0.4640 | 200 | 0.0934 | 0.2517 | | 0.5104 | 220 | 0.0942 | 0.2185 | | 0.5568 | 240 | 0.0774 | 0.2469 | | 0.6032 | 260 | 0.1013 | 0.2248 | | 0.6497 | 280 | 0.0781 | 0.2221 | | 0.6961 | 300 | 0.0386 | 0.2362 | | 0.7425 | 320 | 0.084 | 0.2386 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.12 - SetFit: 1.0.3 - Sentence Transformers: 3.1.0 - spaCy: 3.7.6 - Transformers: 4.39.0 - PyTorch: 2.4.0+cu121 - Datasets: 3.0.0 - 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} } ```