--- base_model: BAAI/bge-small-en-v1.5 library_name: setfit metrics: - accuracy pipeline_tag: text-classification tags: - setfit - absa - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: is the best French food you will find:It may be a bit packed on weekends, but the vibe is good and it is the best French food you will find in the area. - text: knew what the specials were.:Whem asked, we had to ask more detailed questions so that we knew what the specials were. - text: all out wow dining experience.:Go here for a romantic dinner but not for an all out wow dining experience. - text: vibe, the owner is super friendly:Best of all is the warm vibe, the owner is super friendly and service is fast. - text: all of the dishes are excellent.:The menu is limited but almost all of the dishes are excellent. inference: false --- # SetFit Polarity Model with BAAI/bge-small-en-v1.5 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) as the Sentence Transformer embedding model. 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 - **Sentence Transformer body:** [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance - **spaCy Model:** en_core_web_lg - **SetFitABSA Aspect Model:** [omymble/train-bge-small-aspect](https://huggingface.co/omymble/train-bge-small-aspect) - **SetFitABSA Polarity Model:** [omymble/train-bge-small-polarity](https://huggingface.co/omymble/train-bge-small-polarity) - **Maximum Sequence Length:** 512 tokens - **Number of Classes:** 4 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 | | | neutral | | | conflict | | ## 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( "omymble/train-bge-small-aspect", "omymble/train-bge-small-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 | 21.3594 | 43 | | Label | Training Sample Count | |:---------|:----------------------| | conflict | 2 | | negative | 19 | | neutral | 25 | | positive | 82 | ### Training Hyperparameters - batch_size: (16, 2) - 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: 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 | |:------:|:----:|:-------------:|:---------------:| | 0.0018 | 1 | 0.1928 | - | | 0.0923 | 50 | 0.1598 | - | | 0.1845 | 100 | 0.2004 | - | | 0.2768 | 150 | 0.0221 | - | | 0.3690 | 200 | 0.0071 | - | | 0.4613 | 250 | 0.0046 | - | | 0.5535 | 300 | 0.005 | - | | 0.6458 | 350 | 0.0029 | - | | 0.7380 | 400 | 0.0083 | - | | 0.8303 | 450 | 0.0012 | - | | 0.9225 | 500 | 0.0022 | - | ### Framework Versions - Python: 3.10.12 - SetFit: 1.0.3 - Sentence Transformers: 3.0.1 - spaCy: 3.7.4 - Transformers: 4.39.0 - PyTorch: 2.3.1+cu121 - Datasets: 2.20.0 - 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} } ```