pahri's picture
Add SetFit ABSA model
cd033bb verified
|
raw
history blame
9.82 kB
metadata
library_name: setfit
tags:
  - setfit
  - absa
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: >-
      yg sama. Rasanya konsisten dari dulu:Kalo ke Bandung, wajib banget nyobain
      makan siang disini. Tempatnya selalu ramee walau cabangnya ada bbrp di 1
      jalan yg sama. Rasanya konsisten dari dulu mah, enakkk! Ayam bakar sama
      sayur asem wajib dipesen. Dan sambelnya yg selalu juara pedesnya, siap2
      keringetan
  - text: >-
      jam lebih dan tempatnya panas. Makanannya:Di satu deretan ada 3 warung bu
      imas dan rame semua Nunggu makan dateng sekitar 1 jam lebih dan tempatnya
      panas. Makanannya sebenarnya enak2 semua tapi kalo harus antri lama dan
      temptnya kurang oke mending cari warung makan sunda lain
  - text: >-
      Dari makanan yang luar biasa:Dari makanan yang luar biasa, hingga suasana
      yang hangat, hingga layanan yang ramah, tempat lingkungan pusat kota ini
      tidak ketinggalan.
  - text: >-
      Favorite sambal terasi dadak di Bandung sejauh:Favorite sambal terasi
      dadak di Bandung sejauh ini Harganya pun ramah. Next time balik lagi.
  - text: >-
      ayam goreng/ati-ampela goreng gurih asinnya pas:Rasa ayam
      goreng/ati-ampela goreng gurih asinnya pas, sayur asem yang isinya banyak
      dan ras asam-manisnya nyambung, dan sambal leunca-nya enak beutullll....
      Pakai petai dan tempe/tahu lebih sempurna.
pipeline_tag: text-classification
inference: false
model-index:
  - name: SetFit Polarity Model
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.8636363636363636
            name: Accuracy

SetFit Polarity Model

This is a SetFit model that can be used for Aspect Based Sentiment Analysis (ABSA). 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
positive
  • 'air krispi dan ayam bakar:Warung Sunda murah meriah dan makanannya enak. Favorit selada air krispi dan ayam bakar'
  • 'Ayam bakar,sambel leunca:Ayam bakar,sambel leunca sambel terasi merah enak banget 9/10, perkedel jagung 8/10 makan pakai sambel mantap. Makan berdua sekitar 77k'
  • ',sambel leunca sambel terasi merah enak banget 9:Ayam bakar,sambel leunca sambel terasi merah enak banget 9/10, perkedel jagung 8/10 makan pakai sambel mantap. Makan berdua sekitar 77k'
negative
  • ', minus di menu tidak di cantumkan:Makanan biasa saja, minus di menu tidak di cantumkan harga. Posi nasi standar, kelebihan sambal sudah disediakan di mangkok. '
  • 'lebih diatur kah antriannya, kayanya pakai:It wasnt bad food at all. Tapi please mungkin bisa lebih diatur kah antriannya, kayanya pakai waiting list gak sesulit itu deh.'
  • 'rasanya standar. Harga bisa dibilang murah:Tahu tempe perkedel rasanya standar. Harga bisa dibilang murah. Kalau yang masih penasaran ya boleh dateng coba tapi menurut saya overall biasa saja, tidak nemu wah nya dimana..'

Evaluation

Metrics

Label Accuracy
all 0.8636

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(
    "pahri/setfit-indo-resto-RM-ibu-imas-aspect",
    "pahri/setfit-indo-resto-RM-ibu-imas-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 7 35.3922 90
Label Training Sample Count
konflik 0
negatif 0
netral 0
positif 0

Training Hyperparameters

  • batch_size: (6, 6)
  • 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: False

Training Results

Epoch Step Training Loss Validation Loss
0.0036 1 0.2676 -
0.1799 50 0.0064 -
0.3597 100 0.0015 -
0.5396 150 0.0007 -
0.7194 200 0.0005 -
0.8993 250 0.0006 -

Framework Versions

  • Python: 3.10.13
  • SetFit: 1.0.3
  • Sentence Transformers: 2.7.0
  • spaCy: 3.7.4
  • Transformers: 4.36.2
  • PyTorch: 2.1.2
  • Datasets: 2.18.0
  • 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}
}