metadata

library_name: setfit
tags:
  - setfit
  - absa
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
base_model: BAAI/bge-small-en-v1.5
metrics:
  - accuracy
widget:
  - text: >-
      People:Based partly on Chinese military journals, internal speeches by
      senior People's Liberation Army (PLA) officers, and patent data, the paper
      charts more than 50 years of the PLA navy's often-glacial nuclear
      submarine development.
  - text: >-
      Qingdao:Chinese Navy's nuclear-powered submarine Long March 11 takes part
      in a naval parade off the eastern port city of Qingdao to mark the 70th
      anniversary of the founding of the Chinese People's Liberation Army Navy.
  - text: >-
      warfare drills:Anti-submarine warfare drills are increasing, as are
      deployments of sub-hunting P-8 Poseidon aircraft around Southeast Asia and
      the Indian Ocean.
  - text: >-
      devices:The research also details potential breakthroughs in specific
      areas, including pump-jet propulsion and internal quieting devices, based
      on 'imitative innovation' of Russian technology.
  - text: >-
      axe 73,800 jobs:State-run miner Coal India Limited (CIL), which has the
      biggest workforce among listed government undertakings, is likely to axe
      73,800 jobs by 2050 as India pledges to move from fossil fuels to green
      power, according to a research report released by the US-based think tank
      Global Energy Monitor (GEM) on October 10.
pipeline_tag: text-classification
inference: false
model-index:
  - name: SetFit Aspect Model with BAAI/bge-small-en-v1.5
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.7874720357941835
            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
spaCy Model: en_core_web_lg
SetFitABSA Aspect Model: asadnaqvi/setfitabsa-aspect
SetFitABSA Polarity Model: asadnaqvi/setfitabsa-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	"visit:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair." "Mohammed bin Salman:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair." 'legitimacy:The trip to India is evidently timed to burnish his legitimacy after the international opprobrium that followed the murder of The Washington Post journalist Jamal Khashoggi.'
no aspect	"Saudi Arabia:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair." "MBS:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair." "India:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."

Label

Examples

aspect

"visit:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."
"Mohammed bin Salman:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."
'legitimacy:The trip to India is evidently timed to burnish his legitimacy after the international opprobrium that followed the murder of The Washington Post journalist Jamal Khashoggi.'

no aspect

"Saudi Arabia:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."
"MBS:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."
"India:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."

Evaluation

Metrics

Label	Accuracy
all	0.7875

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(
    "asadnaqvi/setfitabsa-aspect",
    "asadnaqvi/setfitabsa-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	8	25.2939	40

Label	Training Sample Count
no aspect	248
aspect	99

Training Hyperparameters

batch_size: (128, 128)
num_epochs: (5, 5)
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
0.0018	1	0.2598	-
0.0893	50	0.2458	0.2552
0.1786	100	0.2418	0.2527
0.2679	150	0.2427	0.2459
0.3571	200	0.1272	0.2566
0.4464	250	0.0075	0.3028
0.5357	300	0.0023	0.3251
0.625	350	0.0021	0.328
0.7143	400	0.0037	0.355

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
SetFit: 1.0.3
Sentence Transformers: 2.7.0
spaCy: 3.7.4
Transformers: 4.40.1
PyTorch: 2.2.1+cu121
Datasets: 2.19.0
Tokenizers: 0.19.1

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}
}