Add SetFit ABSA model

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,280 @@
+---
+library_name: setfit
+tags:
+- setfit
+- absa
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+metrics:
+- accuracy
+widget:
+- text: di area tersebut makanan perancis:mungkin agak ramai di akhir pekan, tapi
+    suasana bagus dan ini adalah makanan prancis terbaik yang bisa anda temukan di
+    area tersebut makanan perancis
+- text: para pelayan dan pemilik tidak:para pelayan dan pemilik tidak peduli tentang
+    hal ini dan berjanji untuk memanggil pembasmi tetapi tidak kecewa atau meminta
+    maaf seperti yang saya harapkan.
+- text: suasana ramai tapi suasana:suasana ramai tapi suasana seperti bistro.
+- text: menyukai artisanal! tarif perancis:jika anda menyukai anggur dan keju serta
+    hidangan prancis yang lezat, anda akan menyukai artisanal! tarif perancis
+- text: hebat lagi, harga juga sangat terjangkau:hebat lagi, harga juga sangat terjangkau,
+    dan makanan sangat enak.
+pipeline_tag: text-classification
+inference: false
+base_model: firqaaa/indo-sentence-bert-base
+model-index:
+- name: SetFit Polarity Model with firqaaa/indo-sentence-bert-base
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.6836734693877551
+      name: Accuracy
+---
+
+# SetFit Polarity Model with firqaaa/indo-sentence-bert-base
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [firqaaa/indo-sentence-bert-base](https://huggingface.co/firqaaa/indo-sentence-bert-base) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) 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](https://www.sbert.net) 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 Type:** SetFit
+- **Sentence Transformer body:** [firqaaa/indo-sentence-bert-base](https://huggingface.co/firqaaa/indo-sentence-bert-base)
+- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
+- **spaCy Model:** id_core_news_trf
+- **SetFitABSA Aspect Model:** [firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-aspect](https://huggingface.co/firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-aspect)
+- **SetFitABSA Polarity Model:** [firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-polarity](https://huggingface.co/firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-polarity)
+- **Maximum Sequence Length:** 512 tokens
+- **Number of Classes:** 4 classes
+<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
+- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
+- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
+
+### Model Labels
+| Label   | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+|:--------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| netral  | <ul><li>'sangat kecil sehingga reservasi adalah suatu keharusan:restoran ini sangat kecil sehingga reservasi adalah suatu keharusan.'</li><li>'di dekat seorang busboy dan mendesiskan rapido:di sebelah kanan saya, nyo rumah berdiri di dekat seorang busboy dan mendesiskan rapido, rapido ketika dia mencoba membersihkan dan mengatur ulang meja untuk enam orang.'</li><li>'dan mengatur ulang meja untuk enam orang:di sebelah kanan saya, nyo rumah berdiri di dekat seorang busboy dan mendesiskan rapido, rapido ketika dia mencoba membersihkan dan mengatur ulang meja untuk enam orang.'</li></ul> |
+| negatif | <ul><li>'untuk enam orang nyonya rumah:di sebelah kanan saya, nyo rumah berdiri di dekat seorang busboy dan mendesiskan rapido, rapido ketika dia mencoba membersihkan dan mengatur ulang meja untuk enam orang nyonya rumah'</li><li>'setelah berurusan dengan pizza di bawah standar:setelah berurusan dengan pizza di bawah standar di seluruh lingkungan kensington - saya menemukan sedikit tonino.'</li><li>'mereka tidak mejikan bir, anda harus:perhatikan bahwa mereka tidak mejikan bir, anda harus membawa sendiri.'</li></ul>                                                                       |
+| positif | <ul><li>'saya tidak menyukai gnocchi.:saya tidak menyukai gnocchi.'</li><li>'dari makanan pembuka yang kami makan:dari makanan pembuka yang kami makan, dim sum, dan variasi makanan lain, tidak mungkin untuk mengkritik makanan tersebut.'</li><li>'kami makan, dim sum, dan variasi:dari makanan pembuka yang kami makan, dim sum, dan variasi makanan lain, tidak mungkin untuk mengkritik makanan tersebut.'</li></ul>                                                                                                                                                                                     |
+| konflik | <ul><li>'makanan enak tapi jangan:makanan enak tapi jangan datang ke sini dengan perut kosong.'</li><li>'milik pihak rumah tagihan:namun, setiap perselisihan tentang ruu itu diimbangi oleh takaran minuman keras yang anda tuangkan sendiri yang merupakan milik pihak rumah tagihan'</li><li>'layanan meja bisa menjadi sedikit:layanan meja bisa menjadi sedikit lebih penuh perhatian tetapi sebagai seseorang yang juga bekerja di industri jasa, saya mengerti mereka sedang sibuk.'</li></ul>                                                                                                           |
+
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.6837   |
+
+## Uses
+
+### Direct Use for Inference
+
+First install the SetFit library:
+
+```bash
+pip install setfit
+```
+
+Then you can load this model and run inference.
+
+```python
+from setfit import AbsaModel
+
+# Download from the 🤗 Hub
+model = AbsaModel.from_pretrained(
+    "firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-aspect",
+    "firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-polarity",
+)
+# Run inference
+preds = model("The food was great, but the venue is just way too busy.")
+```
+
+<!--
+### Downstream Use
+
+*List how someone could finetune this model on their own dataset.*
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Set Metrics
+| Training set | Min | Median  | Max |
+|:-------------|:----|:--------|:----|
+| Word count   | 3   | 20.9935 | 62  |
+
+| Label   | Training Sample Count |
+|:--------|:----------------------|
+| konflik | 21                    |
+| negatif | 243                   |
+| netral  | 186                   |
+| positif | 626                   |
+
+### Training Hyperparameters
+- batch_size: (32, 32)
+- num_epochs: (1, 1)
+- 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 |
+|:----------:|:-------:|:-------------:|:---------------:|
+| 0.0000     | 1       | 0.2996        | -               |
+| 0.0024     | 50      | 0.2488        | -               |
+| 0.0048     | 100     | 0.2636        | -               |
+| 0.0071     | 150     | 0.2544        | -               |
+| 0.0095     | 200     | 0.2036        | -               |
+| 0.0119     | 250     | 0.2002        | -               |
+| 0.0143     | 300     | 0.1723        | -               |
+| 0.0167     | 350     | 0.2112        | -               |
+| 0.0191     | 400     | 0.1655        | -               |
+| 0.0214     | 450     | 0.1559        | -               |
+| **0.0238** | **500** | **0.0602**    | **0.2033**      |
+| 0.0262     | 550     | 0.1047        | -               |
+| 0.0286     | 600     | 0.1228        | -               |
+| 0.0310     | 650     | 0.1152        | -               |
+| 0.0333     | 700     | 0.0444        | -               |
+| 0.0357     | 750     | 0.0479        | -               |
+| 0.0381     | 800     | 0.065         | -               |
+| 0.0405     | 850     | 0.0417        | -               |
+| 0.0429     | 900     | 0.0647        | -               |
+| 0.0452     | 950     | 0.0517        | -               |
+| 0.0476     | 1000    | 0.0433        | 0.2399          |
+| 0.0500     | 1050    | 0.0044        | -               |
+| 0.0524     | 1100    | 0.0241        | -               |
+| 0.0548     | 1150    | 0.0204        | -               |
+| 0.0572     | 1200    | 0.0532        | -               |
+| 0.0595     | 1250    | 0.0116        | -               |
+| 0.0619     | 1300    | 0.0288        | -               |
+| 0.0643     | 1350    | 0.0125        | -               |
+| 0.0667     | 1400    | 0.0357        | -               |
+| 0.0691     | 1450    | 0.0028        | -               |
+| 0.0714     | 1500    | 0.027         | 0.2564          |
+| 0.0738     | 1550    | 0.0032        | -               |
+| 0.0762     | 1600    | 0.0048        | -               |
+| 0.0786     | 1650    | 0.0003        | -               |
+| 0.0810     | 1700    | 0.0008        | -               |
+| 0.0834     | 1750    | 0.0008        | -               |
+| 0.0857     | 1800    | 0.0023        | -               |
+| 0.0881     | 1850    | 0.0003        | -               |
+| 0.0905     | 1900    | 0.0004        | -               |
+| 0.0929     | 1950    | 0.0003        | -               |
+| 0.0953     | 2000    | 0.0054        | 0.2812          |
+| 0.0976     | 2050    | 0.0005        | -               |
+| 0.1000     | 2100    | 0.0006        | -               |
+| 0.1024     | 2150    | 0.0004        | -               |
+| 0.1048     | 2200    | 0.0019        | -               |
+| 0.1072     | 2250    | 0.0007        | -               |
+| 0.1095     | 2300    | 0.0004        | -               |
+| 0.1119     | 2350    | 0.0001        | -               |
+| 0.1143     | 2400    | 0.0004        | -               |
+| 0.1167     | 2450    | 0.0069        | -               |
+| 0.1191     | 2500    | 0.0001        | 0.2845          |
+| 0.1215     | 2550    | 0.0           | -               |
+| 0.1238     | 2600    | 0.0002        | -               |
+| 0.1262     | 2650    | 0.0001        | -               |
+| 0.1286     | 2700    | 0.0109        | -               |
+| 0.1310     | 2750    | 0.0037        | -               |
+| 0.1334     | 2800    | 0.0001        | -               |
+| 0.1357     | 2850    | 0.0001        | -               |
+| 0.1381     | 2900    | 0.0001        | -               |
+| 0.1405     | 2950    | 0.0001        | -               |
+| 0.1429     | 3000    | 0.0001        | 0.2839          |
+
+* The bold row denotes the saved checkpoint.
+### Framework Versions
+- Python: 3.10.13
+- SetFit: 1.0.3
+- Sentence Transformers: 2.2.2
+- spaCy: 3.7.4
+- Transformers: 4.36.2
+- PyTorch: 2.1.2+cu121
+- Datasets: 2.16.1
+- Tokenizers: 0.15.0
+
+## Citation
+
+### BibTeX
+```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}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "models/step_500/",
+  "_num_labels": 5,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.20.1",
+    "pytorch": "1.11.0"
+  }
+}

config_setfit.json

@@ -0,0 +1,11 @@
+{
+  "labels": [
+    "konflik",
+    "negatif",
+    "netral",
+    "positif"
+  ],
+  "spacy_model": "id_core_news_trf",
+  "span_context": 3,
+  "normalize_embeddings": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e75903b9d43b34a9602d4470583b192ab954eaad3938be8194373d688bd884c
+size 497787752

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f44ec07fb9b9dace9551bb690bc911ad26d46608df4ea725d60dc16975f68e
+size 25543

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}