tomaarsen's picture
tomaarsen HF staff
Add SetFit ABSA model
e07f136
metadata
language: en
license: apache-2.0
library_name: setfit
tags:
  - setfit
  - absa
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
datasets:
  - tomaarsen/setfit-absa-semeval-restaurants
metrics:
  - accuracy
widget:
  - text: >-
      (both in quantity AND quality):The Prix Fixe menu is worth every penny and
      you get more than enough (both in quantity AND quality).
  - text: >-
      over 100 different beers to offer thier:The have over 100 different beers
      to offer thier guest so that made my husband very happy and the food was
      delicious, if I must recommend a dish it must be the pumkin tortelini.
  - text: >-
      back with a plate of dumplings.:Get your food to go, find a bench, and
      kick back with a plate of dumplings.
  - text: >-
      the udon was soy sauce and water.:The soup for the udon was soy sauce and
      water.
  - text: >-
      times for the beef cubes - they're:i've been back to nha trang literally a
      hundred times for the beef cubes - they're that good.
pipeline_tag: text-classification
inference: false
co2_eq_emissions:
  emissions: 15.732253126728272
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
  ram_total_size: 31.777088165283203
  hours_used: 0.174
  hardware_used: 1 x NVIDIA GeForce RTX 3090
base_model: BAAI/bge-small-en-v1.5
model-index:
  - name: >-
      SetFit Polarity Model with BAAI/bge-small-en-v1.5 on SemEval 2014 Task 4
      (Restaurants)
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: SemEval 2014 Task 4 (Restaurants)
          type: tomaarsen/setfit-absa-semeval-restaurants
          split: test
        metrics:
          - type: accuracy
            value: 0.748561042108452
            name: Accuracy

SetFit Polarity Model with BAAI/bge-small-en-v1.5 on SemEval 2014 Task 4 (Restaurants)

This is a SetFit model trained on the SemEval 2014 Task 4 (Restaurants) dataset 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 classifying aspect polarities.

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 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 Sources

Model Labels

Label Examples
negative
  • 'But the staff was so horrible:But the staff was so horrible to us.'
  • ', forgot our toast, left out:They did not have mayonnaise, forgot our toast, left out ingredients (ie cheese in an omelet), below hot temperatures and the bacon was so over cooked it crumbled on the plate when you touched it.'
  • 'did not have mayonnaise, forgot our:They did not have mayonnaise, forgot our toast, left out ingredients (ie cheese in an omelet), below hot temperatures and the bacon was so over cooked it crumbled on the plate when you touched it.'
positive
  • "factor was the food, which was: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."
  • "The food is uniformly exceptional: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."
  • "a very capable kitchen which will proudly: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."
neutral
  • "'s on the menu or not.: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."
  • 'to sample both meats).:Our agreed favorite is the orrechiete with sausage and chicken (usually the waiters are kind enough to split the dish in half so you get to sample both meats).'
  • 'to split the dish in half so:Our agreed favorite is the orrechiete with sausage and chicken (usually the waiters are kind enough to split the dish in half so you get to sample both meats).'
conflict
  • 'The food was delicious but:The food was delicious but do not come here on a empty stomach.'
  • "The service varys from day:The service varys from day to day- sometimes they're very nice, and sometimes not."
  • 'Though the Spider Roll may look like:Though the Spider Roll may look like a challenge to eat, with soft shell crab hanging out of the roll, it is well worth the price you pay for them.'

Evaluation

Metrics

Label Accuracy
all 0.7486

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(
    "tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-aspect",
    "tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-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 22.4980 51
Label Training Sample Count
conflict 6
negative 43
neutral 36
positive 170

Training Hyperparameters

  • batch_size: (256, 256)
  • num_epochs: (5, 5)
  • max_steps: 5000
  • 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
0.0078 1 0.2397 -
0.3876 50 0.2252 -
0.7752 100 0.1896 0.1883
1.1628 150 0.0964 -
1.5504 200 0.0307 0.1792
1.9380 250 0.0275 -
2.3256 300 0.0138 0.2036
2.7132 350 0.006 -
3.1008 400 0.0035 0.2287
3.4884 450 0.0015 -
3.8760 500 0.0016 0.2397
4.2636 550 0.001 -
4.6512 600 0.0009 0.2477
  • The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

  • Carbon Emitted: 0.016 kg of CO2
  • Hours Used: 0.174 hours

Training Hardware

  • On Cloud: No
  • GPU Model: 1 x NVIDIA GeForce RTX 3090
  • CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
  • RAM Size: 31.78 GB

Framework Versions

  • Python: 3.9.16
  • SetFit: 1.0.0.dev0
  • Sentence Transformers: 2.2.2
  • spaCy: 3.7.2
  • Transformers: 4.29.0
  • PyTorch: 1.13.1+cu117
  • Datasets: 2.15.0
  • Tokenizers: 0.13.3

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}
}