Update README.md

README.md

@@ -22,29 +22,29 @@ tags:
 # Jeju Satoru
 
 ## Project Overview
-[cite_start]'Jeju Satoru' is a **bidirectional Jeju-Standard Korean translation model** developed to preserve the Jeju language, which is designated as an **'endangered language'** by UNESCO[cite: 17, 256]. [cite_start]The model aims to bridge the digital divide for elderly Jeju dialect speakers by improving their digital accessibility[cite: 257].
+'Jeju Satoru' is a **bidirectional Jeju-Standard Korean translation model** developed to preserve the Jeju language, which is designated as an **'endangered language'** by UNESCO. The model aims to bridge the digital divide for elderly Jeju dialect speakers by improving their digital accessibility.
 
 ## Model Information
 * **Base Model**: KoBART (`gogamza/kobart-base-v2`)
 * **Model Architecture**: Seq2Seq (Encoder-Decoder structure)
-* [cite_start]**Training Data**: The model was trained using a large-scale dataset of approximately 930,000 sentence pairs[cite: 56, 144]. [cite_start]The dataset was built by leveraging the publicly available [Junhoee/Jeju-Standard-Translation](https://huggingface.co/datasets/Junhoee/Jeju-Standard-Translation) dataset, which is primarily based on text from the KakaoBrain JIT (Jeju-Island-Translation) corpus and transcribed data from the AI Hub Jeju dialect speech dataset[cite: 281, 282].
+* **Training Data**: The model was trained using a large-scale dataset of approximately 930,000 sentence pairs. The dataset was built by leveraging the publicly available [Junhoee/Jeju-Standard-Translation](https://huggingface.co/datasets/Junhoee/Jeju-Standard-Translation) dataset, which is primarily based on text from the KakaoBrain JIT (Jeju-Island-Translation) corpus and transcribed data from the AI Hub Jeju dialect speech dataset.
 
 ## Training Strategy and Parameters
-[cite_start]Our model was trained using a **two-stage domain adaptation method** to handle the complexities of the Jeju dialect[cite: 163, 164, 165, 173].
+Our model was trained using a **two-stage domain adaptation method** to handle the complexities of the Jeju dialect.
 
-1. [cite_start]**Domain Adaptation**: The model was separately trained on Standard Korean and Jeju dialect sentences to help it deeply understand the grammar and style of each language[cite: 166, 167, 168, 170, 171, 172].
-2. [cite_start]**Translation Fine-Tuning**: The final stage involved training the model on the bidirectional dataset, with `[제주]` (Jeju) and `[표준]` (Standard) tags added to each sentence to explicitly guide the translation direction[cite: 71, 72, 73, 175, 176].
+1. **Domain Adaptation**: The model was separately trained on Standard Korean and Jeju dialect sentences to help it deeply understand the grammar and style of each language.
+2. **Translation Fine-Tuning**: The final stage involved training the model on the bidirectional dataset, with `[제주]` (Jeju) and `[표준]` (Standard) tags added to each sentence to explicitly guide the translation direction.
 
 The following key hyperparameters and techniques were applied for performance optimization:
-* [cite_start]**Learning Rate**: 2e-5 [cite: 179]
-* [cite_start]**Epochs**: 3 [cite: 180]
-* [cite_start]**Batch Size**: 128 [cite: 178]
-* [cite_start]**Weight Decay**: 0.01 [cite: 179, 180]
+* **Learning Rate**: 2e-5
+* **Epochs**: 3
+* **Batch Size**: 128
+* **Weight Decay**: 0.01
 * **Generation Beams**: 5
 * **GPU Memory Efficiency**: Mixed-precision training (FP16) was used to reduce training time, along with Gradient Accumulation (Steps: 16).
 
 ## Performance Evaluation
-[cite_start]The model's performance was comprehensively evaluated using both quantitative and qualitative metrics[cite: 191, 192, 193].
+The model's performance was comprehensively evaluated using both quantitative and qualitative metrics.
 
 ### Quantitative Evaluation
 | Direction                | SacreBLEU | CHRF   | BERTScore |
@@ -53,9 +53,9 @@ The following key hyperparameters and techniques were applied for performance op
 | Standard → Jeju Dialect  | 64.86     | 72.68  | 0.94      |
 
 ### Qualitative Evaluation (Summary)
-* [cite_start]**Adequacy**: The model accurately captures the meaning of most source sentences[cite: 216, 217].
-* [cite_start]**Fluency**: The translated sentences are grammatically correct and natural-sounding[cite: 219, 220, 221, 222].
-* [cite_start]**Tone**: While generally good at maintaining the tone, the model has some limitations in perfectly reflecting the nuances and specific colloquial endings of the Jeju dialect[cite: 223, 224, 225].
+* **Adequacy**: The model accurately captures the meaning of most source sentences.
+* **Fluency**: The translated sentences are grammatically correct and natural-sounding.
+* **Tone**: While generally good at maintaining the tone, the model has some limitations in perfectly reflecting the nuances and specific colloquial endings of the Jeju dialect.
 
 ## How to Use
 You can easily load and infer with the model using the `transformers` library's `pipeline` function.