Atualização README

README.md

@@ -1,7 +1,7 @@
 ---
 language:
   - yrl
-license: cc-by-4.0
+license: cc-by-nc-4.0
 pipeline_tag: token-classification
 tags:
   - named-entity-recognition
@@ -38,12 +38,187 @@ widget:
   - text: "Asuí kwá mukũi apigawa-itá aintá usemu kaá kití aintá upurakí arama balata, asuí mairamé aintá usika ana iwitera rupitá-pe, ape aintá umaã siya kumã iwa-itá."
 ---
 
+# Canarim-Bert-PosTag-Nheengatu
+
 <p align="center">
   <img width="350" alt="Camarim Logo" src="https://raw.githubusercontent.com/DominguesM/canarim-bert-nheengatu/main/assets/canarim-yrl-nbg.png">
 </p>
 
-<hr>
+<br/>
 
-# Canarim-Bert-PosTag-Nheengatu
+## About
+
+The `canarim-bert-posTag-nheengatu` model is a part-of-speech tagging model for the Nheengatu language, trained using the `UD_Nheengatu-CompLin` dataset available on [github](https://github.com/UniversalDependencies/UD_Nheengatu-CompLin/). It is based on the tokenizer and the [`Canarim-Bert-Nheengatu`](https://huggingface.co/dominguesm/canarim-bert-nheengatu) model.
+
+## Supported Tags
+
+The model can identify the following grammatical classes:
+
+|**tag**|**abbreviation in glossary**|**expansion of abbreviation**|
+|-------|-----------------------------|-----------------------------|
+|ADJ|adj.|1st class adjective|
+|ADP|posp.|postposition|
+|ADV|adv.|adverb|
+|AUX|aux.|auxiliary|
+|CCONJ|cconj.|coordinating conjunction|
+|DET|det.|determiner|
+|INTJ|interj.|interjection|
+|NOUN|n.|1st class noun|
+|NUM|num.|numeral|
+|PART|part.|particle|
+|PRON|pron.|1st class pronoun|
+|PROPN|prop.|proper noun|
+|PUNCT|punct.|punctuation|
+|SCONJ|sconj.|subordinating conjunction|
+|VERB|v.|1st class verb|
+
+## Training
+
+### Dataset
+
+The dataset used for training was the [`UD_Nheengatu-CompLin`](https://github.com/UniversalDependencies/UD_Nheengatu-CompLin/), divided into 80/10/10 proportions for training, evaluation, and testing, respectively.
+
+
+```
+DatasetDict({
+    train: Dataset({
+        features: ['id', 'tokens', 'pos_tags', 'text'],
+        num_rows: 1068
+    })
+    test: Dataset({
+        features: ['id', 'tokens', 'pos_tags', 'text'],
+        num_rows: 134
+    })
+    eval: Dataset({
+        features: ['id', 'tokens', 'pos_tags', 'text'],
+        num_rows: 134
+    })
+})
+```
+
+### Hyperparameters
+
+The hyperparameters used for training were:
+
+* `learning_rate`: 3e-4
+* `train_batch_size`: 16
+* `eval_batch_size`: 32
+* `gradient_accumulation_steps`: 1
+* `weight_decay`: 0.01
+* `num_train_epochs`: 10
+
+### Results
+
+The training and validation loss over the steps can be seen below:
+
+<p align="center">
+  <img width="600" alt="Train Loss" src="https://raw.githubusercontent.com/DominguesM/canarim-bert-nheengatu/main/assets/postag-train-loss.png">
+</p>
+
+<p align="center">
+  <img width="600" alt="Eval Loss" src="https://raw.githubusercontent.com/DominguesM/canarim-bert-nheengatu/main/assets/postag-eval-loss.png">
+</p>
+
+The model's results on the evaluation set can be viewed below:
+
+```
+{
+  'eval_loss': 0.5337784886360168,
+  'eval_precision': 0.913735899137359,
+  'eval_recall': 0.913735899137359,
+  'eval_f1': 0.913735899137359,
+  'eval_accuracy': 0.913735899137359,
+  'eval_runtime': 0.1957,
+  'eval_samples_per_second': 684.883,
+  'eval_steps_per_second': 25.555,
+  'epoch': 10.0
+}
+```
+
+### Metrics
+
+The model's evaluation metrics on the test set can be viewed below:
+
+```
+                precision    recall  f1-score   support
+
+         ADJ     0.7895    0.6522    0.7143        23
+         ADP     0.9355    0.9158    0.9255        95
+         ADV     0.8261    0.8172    0.8216        93
+         AUX     0.9444    0.9189    0.9315        37
+       CCONJ     0.7778    0.8750    0.8235         8
+         DET     0.8776    0.9149    0.8958        47
+        INTJ     0.5000    0.5000    0.5000         4
+        NOUN     0.9257    0.9222    0.9239       270
+         NUM     1.0000    0.6667    0.8000         6
+        PART     0.9775    0.9062    0.9405        96
+        PRON     0.9568    1.0000    0.9779       155
+       PROPN     0.6429    0.4286    0.5143        21
+       PUNCT     0.9963    1.0000    0.9981       267
+       SCONJ     0.8000    0.7500    0.7742        32
+        VERB     0.8651    0.9347    0.8986       199
+
+   micro avg     0.9202    0.9202    0.9202      1353
+   macro avg     0.8543    0.8135    0.8293      1353
+weighted avg     0.9191    0.9202    0.9187      1353
+```
+
+<br/>
+
+<p align="center">
+  <img width="600" alt="Canarim BERT Nheengatu - POSTAG - Confusion Matrix" src="https://raw.githubusercontent.com/DominguesM/canarim-bert-nheengatu/main/assets/postag-confusion-matrix.png">
+</p>
+
+## Usage
+
+The use of this model follows the common standards of the [transformers](https://github.com/huggingface/transformers) library. To use it, simply install the library and load the model:
+
+
+```python
+from transformers import pipeline
+
+model_name = "dominguesm/canarim-bert-postag-nheengatu"
+
+pipe = pipeline("ner", model=model_name)
+
+pipe("Yamunhã timbiú, yapinaitika, yamunhã kaxirí.", aggregation_strategy="average")
+```
+
+The result will be:
+
+```json
+[
+  {"entity_group": "VERB", "score": 0.999668, "word": "Yamunhã", "start": 0, "end": 7},
+  {"entity_group": "NOUN", "score": 0.99986947, "word": "timbiú", "start": 8, "end": 14},
+  {"entity_group": "PUNCT", "score": 0.99993193, "word": ",", "start": 14, "end": 15},
+  {"entity_group": "VERB", "score": 0.9995308, "word": "yapinaitika", "start": 16, "end": 27},
+  {"entity_group": "PUNCT", "score": 0.9999416, "word": ",", "start": 27, "end": 28},
+  {"entity_group": "VERB", "score": 0.99955815, "word": "yamunhã", "start": 29, "end": 36},
+  {"entity_group": "NOUN", "score": 0.9998684, "word": "kaxirí", "start": 37, "end": 43},
+  {"entity_group": "PUNCT", "score": 0.99997807, "word": ".", "start": 43, "end": 44}
+]
+```
+
+## License
+
+The license of this model follows that of the dataset used for training, which is [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode). For more information, please visit the [dataset repository](https://github.com/UniversalDependencies/UD_Nheengatu-CompLin/tree/master).
+
+
+## References
 
-WIP
+```bibtex
+@inproceedings{stil,
+  author = {Leonel de Alencar},
+  title = {Yauti: A Tool for Morphosyntactic Analysis of Nheengatu within the Universal Dependencies Framework},
+  booktitle = {Anais do XIV Simpósio Brasileiro de Tecnologia da Informação e da Linguagem Humana},
+  location = {Belo Horizonte/MG},
+  year = {2023},
+  keywords = {},
+  issn = {0000-0000},
+  pages = {135--145},
+  publisher = {SBC},
+  address = {Porto Alegre, RS, Brasil},
+  doi = {10.5753/stil.2023.234131},
+  url = {https://sol.sbc.org.br/index.php/stil/article/view/25445}
+}
+```

README_ptbr.md

@@ -0,0 +1,221 @@
+---
+language:
+  - yrl
+license: cc-by-nc-4.0
+pipeline_tag: token-classification
+tags:
+  - named-entity-recognition
+  - Transformer
+  - pytorch
+  - bert
+  - nheengatu
+metrics:
+  - f1
+  - precision
+  - recall
+model-index:
+- name: canarim-bert-postag-nheengatu
+  results:
+  - task:
+      type: named-entity-recognition
+    dataset:
+      type: UD_Nheengatu-CompLin
+      name: UD Nheengatu CompLin
+    metrics:
+      - type: f1
+        value: 82.93
+        name: F1 Score
+      - type: accuracy
+        value: 92.02
+        name: Accuracy
+      - type: recall
+        value: 81.35
+        name: Recall
+widget:
+  - text: "Apigawa i paya waá umurari iké, sera José."
+  - text: "Asú apagari nhaã apigawa supé."
+  - text: "― Taukwáu ra."
+  - text: "Asuí kwá mukũi apigawa-itá aintá usemu kaá kití aintá upurakí arama balata, asuí mairamé aintá usika ana iwitera rupitá-pe, ape aintá umaã siya kumã iwa-itá."
+---
+
+# Canarim-Bert-PosTag-Nheengatu
+
+<p align="center">
+  <img width="350" alt="Camarim Logo" src="https://raw.githubusercontent.com/DominguesM/canarim-bert-nheengatu/main/assets/canarim-yrl-nbg.png">
+</p>
+
+<br/>
+
+## Sobre
+
+O modelo `canarim-bert-posTag-nheengatu` é um modelo de marcação de classe gramatical para a língua Nheengatu que foi treinado no conjunto de dados `UD_Nheengatu-CompLin` disponível no [github](https://github.com/UniversalDependencies/UD_Nheengatu-CompLin/). Foi utilizado como base o tokenizador e o modelo [`Canarim-Bert-Nheengatu`](https://huggingface.co/dominguesm/canarim-bert-nheengatu).
+
+## Etiquetas Suportadas
+
+O modelo é capaz de identificar as seguintes classes gramaticais:
+
+|**etiqueta**|**abreviatura no glossário**|**expansão da abreviatura**|
+|------------|----------------------------|---------------------------|
+|ADJ|adj.|adjetivo de 1ª cl.|
+|ADP|posp.|posposição|
+|ADV|adv.|advérbio|
+|AUX|aux.|auxiliar|
+|CCONJ|cconj.|conjunção coordenativa|
+|DET|det.|determinante|
+|INTJ|interj.|interjeição|
+|NOUN|n.|substantivo de 1ª classe|
+|NUM|num.|numeral|
+|PART|part.|partícula|
+|PRON|pron.|pronome de 1ª classe|
+|PROPN|prop.|substantivo próprio|
+|PUNCT|punct.|pontuação|
+|SCONJ|sconj.|conjunção subordinativa|
+|VERB|v.|verbo de 1ª classe|
+
+## Treinamento
+
+### Conjunto de Dados
+
+O conjunto de dados utilizado para o treinamento foi o [`UD_Nheengatu-CompLin`](https://github.com/UniversalDependencies/UD_Nheengatu-CompLin/), dividido na proporção 80/10/10 para treino, avaliação e teste, respectivamente.
+
+```
+DatasetDict({
+    train: Dataset({
+        features: ['id', 'tokens', 'pos_tags', 'text'],
+        num_rows: 1068
+    })
+    test: Dataset({
+        features: ['id', 'tokens', 'pos_tags', 'text'],
+        num_rows: 134
+    })
+    eval: Dataset({
+        features: ['id', 'tokens', 'pos_tags', 'text'],
+        num_rows: 134
+    })
+})
+```
+
+### Hiperparâmetros
+
+Os hiperparâmetros utilizados para o treinamento foram:
+
+* `learning_rate`: 3e-4
+* `train_batch_size`: 16
+* `eval_batch_size`: 32
+* `gradient_accumulation_steps`: 1
+* `weight_decay`: 0.01
+* `num_train_epochs`: 10
+
+### Resultados
+
+A perca de treinamento e validação ao longo das épocas pode ser visualizada abaixo:
+
+<p align="center">
+  <img width="600" alt="Train Loss" src="https://raw.githubusercontent.com/DominguesM/canarim-bert-nheengatu/main/assets/postag-train-loss.png">
+</p>
+
+<p align="center">
+  <img width="600" alt="Eval Loss" src="https://raw.githubusercontent.com/DominguesM/canarim-bert-nheengatu/main/assets/postag-eval-loss.png">
+</p>
+
+Os resultados do modelo no conjunto de avaliação podem ser visualizados abaixo:
+
+```
+{
+  'eval_loss': 0.5337784886360168,
+  'eval_precision': 0.913735899137359,
+  'eval_recall': 0.913735899137359,
+  'eval_f1': 0.913735899137359,
+  'eval_accuracy': 0.913735899137359,
+  'eval_runtime': 0.1957,
+  'eval_samples_per_second': 684.883,
+  'eval_steps_per_second': 25.555,
+  'epoch': 10.0
+}
+```
+
+### Métricas
+
+As métricas de avaliação do modelo no conjunto de teste podem ser visualizadas abaixo:
+
+```
+                precision    recall  f1-score   support
+
+         ADJ     0.7895    0.6522    0.7143        23
+         ADP     0.9355    0.9158    0.9255        95
+         ADV     0.8261    0.8172    0.8216        93
+         AUX     0.9444    0.9189    0.9315        37
+       CCONJ     0.7778    0.8750    0.8235         8
+         DET     0.8776    0.9149    0.8958        47
+        INTJ     0.5000    0.5000    0.5000         4
+        NOUN     0.9257    0.9222    0.9239       270
+         NUM     1.0000    0.6667    0.8000         6
+        PART     0.9775    0.9062    0.9405        96
+        PRON     0.9568    1.0000    0.9779       155
+       PROPN     0.6429    0.4286    0.5143        21
+       PUNCT     0.9963    1.0000    0.9981       267
+       SCONJ     0.8000    0.7500    0.7742        32
+        VERB     0.8651    0.9347    0.8986       199
+
+   micro avg     0.9202    0.9202    0.9202      1353
+   macro avg     0.8543    0.8135    0.8293      1353
+weighted avg     0.9191    0.9202    0.9187      1353
+```
+
+<br/>
+
+<p align="center">
+  <img width="600" alt="Canarim BERT Nheengatu - POSTAG - Confusion Matrix" src="https://raw.githubusercontent.com/DominguesM/canarim-bert-nheengatu/main/assets/postag-confusion-matrix.png">
+</p>
+
+## Uso
+
+A utilização deste modelo segue os padrões comuns da biblioteca [transformers](https://github.com/huggingface/transformers). Para utilizá-lo, basta instalar a biblioteca e carregar o modelo:
+
+```python
+from transformers import pipeline
+
+model_name = "dominguesm/canarim-bert-postag-nheengatu"
+
+pipe = pipeline("ner", model=model_name)
+
+pipe("Yamunhã timbiú, yapinaitika, yamunhã kaxirí.", aggregation_strategy="average")
+```
+
+O resultado será:
+
+```json
+[
+  {"entity_group": "VERB", "score": 0.999668, "word": "Yamunhã", "start": 0, "end": 7},
+  {"entity_group": "NOUN", "score": 0.99986947, "word": "timbiú", "start": 8, "end": 14},
+  {"entity_group": "PUNCT", "score": 0.99993193, "word": ",", "start": 14, "end": 15},
+  {"entity_group": "VERB", "score": 0.9995308, "word": "yapinaitika", "start": 16, "end": 27},
+  {"entity_group": "PUNCT", "score": 0.9999416, "word": ",", "start": 27, "end": 28},
+  {"entity_group": "VERB", "score": 0.99955815, "word": "yamunhã", "start": 29, "end": 36},
+  {"entity_group": "NOUN", "score": 0.9998684, "word": "kaxirí", "start": 37, "end": 43},
+  {"entity_group": "PUNCT", "score": 0.99997807, "word": ".", "start": 43, "end": 44}
+]
+```
+
+## Licença
+
+A licença deste modelo segue a licença do conjunto de dados utilizado para o treinamento, ou seja, [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode). Para mais informações, acesse o [repositório do conjunto de dados](https://github.com/UniversalDependencies/UD_Nheengatu-CompLin/tree/master)
+
+## Referências
+
+```bibtex
+@inproceedings{stil,
+  author = {Leonel de Alencar},
+  title = {Yauti: A Tool for Morphosyntactic Analysis of Nheengatu within the Universal Dependencies Framework},
+  booktitle = {Anais do XIV Simpósio Brasileiro de Tecnologia da Informação e da Linguagem Humana},
+  location = {Belo Horizonte/MG},
+  year = {2023},
+  keywords = {},
+  issn = {0000-0000},
+  pages = {135--145},
+  publisher = {SBC},
+  address = {Porto Alegre, RS, Brasil},
+  doi = {10.5753/stil.2023.234131},
+  url = {https://sol.sbc.org.br/index.php/stil/article/view/25445}
+}
+```