omymble's picture
Add SetFit ABSA model
e072507 verified
metadata
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: >-
      FOUR DOLLARS:Lahore is a great place to duck into late-night when you need
      some really tasty food on the cheap -- you'll likely have trouble
      finishing the amount of food you get for FOUR DOLLARS.
  - text: >-
      passion:An oasis of refinement:  Food, though somewhat uneven, often
      reaches the pinnacles of new American fine cuisine - chef's passion (and
      kitchen's precise execution) is most evident in the fish dishes and soups.
  - text: >-
      Food:Food is usually very good, though ocasionally I wondered about
      freshmess of raw vegatables in side orders.
  - text: Italian decor:Nice restaurant overall, with classic upscale Italian decor.
  - text: >-
      raw vegatables:Food is usually very good, though ocasionally I wondered
      about freshmess of raw vegatables in side orders.
inference: false

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 Sources

Model Labels

Label Examples
aspect
  • 'staff:But the staff was so horrible to us.'
  • "food:To be completely fair, the only redeeming factor was the food, which was above average, but couldn't make up for all the other deficiencies of Teodora."
  • "food:The food is uniformly exceptional, with a very capable kitchen which will proudly whip up whatever you feel like eating, whether it's on the menu or not."
no aspect
  • "factor:To be completely fair, the only redeeming factor was the food, which was above average, but couldn't make up for all the other deficiencies of Teodora."
  • "deficiencies:To be completely fair, the only redeeming factor was the food, which was above average, but couldn't make up for all the other deficiencies of Teodora."
  • "Teodora:To be completely fair, the only redeeming factor was the food, which was above average, but couldn't make up for all the other deficiencies of Teodora."

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/train-eval-bge-small-aspect",
    "omymble/train-eval-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 4 17.9296 37
Label Training Sample Count
no aspect 71
aspect 128

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
0.0059 1 0.2686 -
0.2959 50 0.1567 0.2585
0.5917 100 0.0103 0.2937
0.8876 150 0.0095 0.2935
  • 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}
}