metadata

library_name: setfit
tags:
  - setfit
  - absa
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: >-
      people:Regardless of whether there are two people or two hundred people
      ahead of you the hostess will take your name and tell you Five minutes.
  - text: >-
      dish:This dish is my favorite and I always get it when I go there and
      never get tired of it.
  - text: >-
      food:Get your food to go, find a bench, and kick back with a plate of
      dumplings.
  - text: >-
      crabmeat lasagna:You must have the crabmeat lasagna which is out of this
      world and the chocolate bread pudding for dessert.
  - text: >-
      plate:Get your food to go, find a bench, and kick back with a plate of
      dumplings.
pipeline_tag: text-classification
inference: false
co2_eq_emissions:
  emissions: 12.403245052695876
  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: 0.158
  hardware_used: 1 x NVIDIA GeForce RTX 3090
base_model: BAAI/bge-small-en-v1.5
model-index:
  - name: SetFit Aspect Model with BAAI/bge-small-en-v1.5
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: SemEval 2014 Task 4 (Restaurants)
          type: tomaarsen/setfit-absa-semeval-restaurants
          split: train[384:]
        metrics:
          - type: accuracy
            value: 0.7871243108660857
            name: Accuracy

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:

Fine-tuning a Sentence Transformer with contrastive learning.
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:

Use a spaCy model to select possible aspect span candidates.
Use this SetFit model to filter these possible aspect span candidates.
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
SetFitABSA Aspect Model: tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-aspect
SetFitABSA Polarity Model: tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-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	'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."

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."

Evaluation

Metrics

Label	Accuracy
all	0.7871

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	4	19.3034	45

Label	Training Sample Count
no aspect	231
aspect	204

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
load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0027	1	0.2574	-
0.1340	50	0.2561	-
0.2681	100	0.251	0.2543
0.4021	150	0.2451	-
0.5362	200	0.242	0.2506
0.6702	250	0.2239	-
0.8043	300	0.0473	0.2499
0.9383	350	0.0098	-
1.0724	400	0.0097	0.2734
1.2064	450	0.0047	-
1.3405	500	0.0071	0.2834
1.4745	550	0.0089	-
1.6086	600	0.005	0.273
1.7426	650	0.0041	-
1.8767	700	0.0042	0.2942
2.0107	750	0.0053	-
2.1448	800	0.0073	0.2898

The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Carbon Emitted: 0.012 kg of CO2
Hours Used: 0.158 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
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}
}