omymble/books-bge-small-aspect

SetFit Aspect Model with BAAI/bge-small-en-v1.5

This is a SetFit model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses BAAI/bge-small-en-v1.5 as the Sentence Transformer embedding model. A LogisticRegression 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 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: BAAI/bge-small-en-v1.5
• Classification head: a LogisticRegression instance
• spaCy Model: en_core_web_lg
• SetFitABSA Aspect Model: omymble/books-bge-small-aspect
• SetFitABSA Polarity Model: omymble/books-bge-small-polarity
• Maximum Sequence Length: 512 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
aspect	"younger ones:It might be an entertaining point of discussion with a child 12 or older, but it's too dark for younger ones, unless you're ready to talk about true evil, adult motivations, supernatural forces, and fratricide!" 'Nix:-enjoy the genre of fantasies, of a unknown world, as Nix weaves a wonderful tale of the things that will open your eyes to a different world' 'mystery:The mystery is secondary to the rest of the story and is only really approached in the remaining 30 pages of the book'
no aspect	"point:It might be an entertaining point of discussion with a child 12 or older, but it's too dark for younger ones, unless you're ready to talk about true evil, adult motivations, supernatural forces, and fratricide!" "discussion:It might be an entertaining point of discussion with a child 12 or older, but it's too dark for younger ones, unless you're ready to talk about true evil, adult motivations, supernatural forces, and fratricide!" "child:It might be an entertaining point of discussion with a child 12 or older, but it's too dark for younger ones, unless you're ready to talk about true evil, adult motivations, supernatural forces, and fratricide!"

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(
    "omymble/books-bge-small-aspect",
    "omymble/books-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	2	24.9558	56

Label	Training Sample Count
no aspect	330
aspect	100

Training Hyperparameters

• batch_size: (128, 128)
• 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: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0011	1	0.2545	-
0.0536	50	0.2497	0.2476
0.1072	100	0.1865	0.2074
0.1608	150	0.0377	0.2288
0.2144	200	0.0343	0.2691
0.2680	250	0.011	0.2619
0.3215	300	0.0107	0.272
0.3751	350	0.0074	0.2738

• The bold row denotes the saved checkpoint.

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

@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}
}