Update app.py

app.py

@@ -518,37 +518,83 @@ def predict_tags(test_sentence):
 predict_tags(test_sentence)
 
 def get_readme():
-    return 
-    """
+    return """
 
-    This is a BERT Tagalog Base Uncased Part of Speech tagger fine-tuned model of [Jiang et. al.'s pre-trained bert-tagalog-base-uncased model](https://huggingface.co/GKLMIP/bert-tagalog-base-uncased).
+    ----
 
-    ## Model Details
+    <!-- ---- -->
 
-    ### Model Description
+    # BERT Tagalog Part of Speech Tagger (BERTTPOST)
+
+    ## 📋 Model Details
 
     <!-- Provide a longer summary of what this model is. -->
+    ### Model Description
 
-    - **Developed by:** syke9p3, mnemoria, xenoxia, riakm
-    - **Shared by:** syke9p3
     - **Model type:** BERT Tagalog Base Uncased
     - **Languages (NLP):** Tagalog, Filipino
-    - **Dataset:** Sagum et. al.'s annotated Tagalog Corpora based on MGNN Tagset convention. This model was trained in 800 sentences and evaluated with 200 sentences.
-    - **Finetuned from model**: [Jiang et. al.'s pre-trained bert-tagalog-base-uncased model](https://huggingface.co/GKLMIP/bert-tagalog-base-uncased)
+    - **Finetuned from model**: [GKLMIP/bert-tagalog-base-uncased](https://huggingface.co/GKLMIP/bert-tagalog-base-uncased)
+
+    ### Dataset
+
+    1000 annotated sentences from Sagum et. al.'s Tagalog Corpora based on MGNN Tagset convention.
+
+    | Dataset        | Number of Sentences | Percentage |
+    |----------------|-----------------|------------|
+    | Training Set   | 800           | 80%        |
+    | Testing Set    | 200             | 20%        |
+
+    ### Preprocessing
+    A corpus was used containing tagged sentences in Tagalog language. The dataset comprises sentences with each word annotated with its corresponding POS tag in the format of ```<TAG word>```. To prepare the corpus for training, the following preprocessing steps were performed:
+    1. **Removal of Line Identifier**: the line identifier, such as ```SNT.108970.2066```, was removed from each tagged sentence.
+    2. **Symbol Conversion**: for the BERT model, certain special symbols like hyphens, quotes, commas, etc., were converted into special tokens (```PMP```, ```PMS```, ```PMC```) to preserve their meaning during tokenization.
+    3. **Alignment of Tokenization**: the BERT tokenized words and their corresponding POS tags were aligned to ensure that the tokenization and tagging are consistent.
+
+
+    ### Training
+
+    This model was trained using PyTorch library with the following hyperparameters set:
+
+    | **Hyperparamter**   |  **Value** |   
+    |---------------- |---------
+    | Batch Size      |  8 |
+    | Training Epoch  |  5 |
+    | Learning-rate   |  2e-5 |
+    | Optimizer       |  Adam |
+
 
-    ## GitHub Link
-    [syke9p3/bert-tagalog-pos-tagger](https://github.com/syke9p3/bert-tagalog-pos-tagger)
+    ## 👥 Developed by
+    - Saya-ang, Kenth G. ([@syke9p3](https://github.com/syke9p3))
+    - Gozum, Denise Julianne S. ([@Xenoxianne](https://github.com/Xenoxianne))
+    - Hamor, Mary Grizelle D. ([@mnemoria](https://github.com/mnemoria))
+    - Mabansag, Ria Karen B. ([@riavx](https://github.com/riavx))
 
-    ### Tags
+    ## ⚒️ Languages and Technologies
+
+    [![Hugging Face](https://img.shields.io/badge/Hugging%20Face%20-FFD21E?style=for-the-badge&logo=huggingface&logoColor=black)](https://jupyter.org/)
+
+    [![Python](https://img.shields.io/badge/Python-F7CC42?style=for-the-badge&logo=python&logoColor=black)](https://www.python.org/)
+
+    [![Gradio](https://img.shields.io/badge/Gradio-F08705?style=for-the-badge&logo=gradio&logoColor=white)](https://pytorch.org/)
+
+    [![Jupyter Notebook](https://img.shields.io/badge/Jupyter%20Notebook-F37626?style=for-the-badge&logo=jupyter&logoColor=white)](https://jupyter.org/)
+
+    [![PyTorch](https://img.shields.io/badge/PyTorch-EE4C2C?style=for-the-badge&logo=pytorch&logoColor=white)](https://pytorch.org/)
+
+
+
+
+
+    ## 🏷️ Tags
 
     | Part of Speech                                 | Tags |
     |-----------------------------------------------|------|
-    | **Noun**                                   | NNC  |
+    | **Noun**                                       | ![NNC](https://img.shields.io/badge/NNC-84CC16?style=for-the-badge&logoColor=white)  |
     | Common Noun                                   | NNC  |
     | Proper Noun                                   | NNP  |
     | Proper Noun Abbreviation                      | NNPA |
     | Common Noun Abbreviation                      | NNCA |
-    | **Pronoun**                                       | PR   |
+    | **Pronoun**                                       | ![PR](https://img.shields.io/badge/PR-0D9488?style=for-the-badge&logoColor=white)     |
     | as Subject (Palagyo)/Personal Pronouns Singular | PRS  |
     | Personal Pronouns                             | PRP  |
     | Possessive Subject (Paari)                    | PRSP |
@@ -559,15 +605,15 @@ def get_readme():
     | Comparison (Panulad)                          | PRC  |
     | Found (Pahimaton)                             | PRF  |
     | Indefinite                                    | PRI  |
-    | **Determiner**       | DT   |
+    | **Determiner**      | ![DT](https://img.shields.io/badge/DT-16A34A?style=for-the-badge&logoColor=white)      |
     | Determiner (Pantukoy) for Common Noun Plural  | DTC  |
     | Determiner (Pantukoy) for Proper Noun         | DTP  |
     | Determiner (Pantukoy) for Proper Noun Plural  | DTPP |
-    | Lexical Marker                                | LM   |
-    | Conjunctions (Pang-ugnay)                     | CC, CCT, CCR, CCB, CCA |
+    | **Conjunctions (Pang-ugnay)**                     | ![CC](https://img.shields.io/badge/CC-16A34ADB2777?style=for-the-badge&logoColor=white)   |
+    | **Lexical Marker**                                | ![LM](https://img.shields.io/badge/LM-EAB308?style=for-the-badge&logoColor=white)     |
     | Ligatures (Pang-angkop)                       | CCP  |
     | Preposition (Pang-ukol)                       | CCU  |
-    | **Verb (Pandiwa)**                                | VB   |
+    | **Verb (Pandiwa)**                                | ![VB](https://img.shields.io/badge/VB-2563EB?style=for-the-badge&logoColor=white)     |
     | Neutral/Infinitive                            | VBW  |
     | Auxiliary, Modal/Pseudo-verbs                 | VBS  |
     | Existential                                  | VBH  |
@@ -582,14 +628,14 @@ def get_readme():
     | Locative Focus                               | VBOL |
     | Instrumental Focus                           | VBOI |
     | Referential/Measurement Focus                | VBRF |
-    | **Adjective (Pang-uri)**                         | JJ   |
+    | **Adjective**                     | ![JJ](https://img.shields.io/badge/JJ-0D9488?style=for-the-badge&logoColor=white)    |
     | Describing (Panlarawan)                      | JJD  |
     | Used for Comparison (same level) (Pahambing Magkatulad) | JJC  |
     | Comparison Comparative (more) (Palamang)     | JJCC |
     | Comparison Superlative (most) (Pasukdol)      | JJCS |
     | Comparison Negation (not quite) (Di-Magkatulad) | JJCN |
     | Describing Number (Pamilang)                 | JJN  |
-    | **Adverb (Pang-Abay)**                           | RB   |
+    | **Adverb (Pang-Abay)**                           | ![RB](https://img.shields.io/badge/RB-DB2777?style=for-the-badge&logoColor=white)    |
     | Describing “How” (Pamaraan)                  | RBD  |
     | Number (Panggaano/Panukat)                   | RBN  |
     | Conditional (Kondisyunal)                   | RBK  |
@@ -605,18 +651,22 @@ def get_readme():
     | Enclitics (Paningit)                         | RBI  |
     | Interjections (Sambitla)                     | RBJ  |
     | Social Formula (Pormularyong Panlipunan)     | RBS  |
-    |**Cardinal Number (Bilang)**                    | CD   |
+    |**Cardinal Number (Bilang)**                    | ![CD](https://img.shields.io/badge/CD-2563EB?style=for-the-badge&logoColor=white)    |
     | Digit, Rank, Count                           | CDB  |
-    | **Topicless (Walang Paksa)**                     | TS   |
-    | Foreign Words                                | FW   |
-    | **Punctuation (Pananda)**                        | PM   |
+    | **Topicless (Walang Paksa)**                     | ![TS](https://img.shields.io/badge/TS-0891B2?style=for-the-badge&logoColor=white)    |
+    | **Foreign Words**                               | ![FW](https://img.shields.io/badge/FW-EA580C?style=for-the-badge&logoColor=white)    |
+    | **Punctuation (Pananda)**                        | ![PM](https://img.shields.io/badge/PM-DB2777?style=for-the-badge&logoColor=white)    |
     | Period                                       | PMP  |
     | Exclamation Point                            | PME  |
     | Question Mark                                | PMQ  |
     | Comma                                        | PMC  |
     | Semi-colon                                   | PMSC |
-    | **Symbols**                                      | PMS  |
+    | Other Symbols                                      | PMS  |
         
+    ## Bias, Risks, and Limitations
+
+    This model has not been fully tested so please use with caution.
+
     """