Update README.md

README.md

@@ -18,133 +18,46 @@ tags:
 
 A state-of-the-art Arabic text style transfer model that transforms text into the writing style of 21 different Arabic authors using descriptive author tokens and prompt engineering.
 
-## 🎯 Model Performance
-
-- **BLEU Score:** 24.58
-- **chrF Score:** 59.01
-- **Competition:** First Place in AraGenEval 2024
-- **Supported Authors:** 21 Arabic authors
-
-## 🚀 Quick Start
-
-### Installation
-
-```bash
-pip install -r requirements.txt
-```
-
-### Basic Usage
-
-```python
-from inference_arabic_author_transfer import ArabicAuthorTextTransfer
+## 🔗 Paper Link (ACL Anthology)
 
-# Initialize model
-model = ArabicAuthorTextTransfer()
+📘 **ANLPers at AraGenEval Shared Task: Descriptive Author Tokens for Transparent Arabic Authorship Style Transfer** [https://aclanthology.org/2025.arabicnlp-sharedtasks.8.pdf]
 
-# Transfer text to author's style
-text = "التعليم مهم جداً في حياتنا اليومية"
-target_author = "يوسف إدريس"
-
-result = model.transfer_style(text, target_author)
-print(f"Original: {text}")
-print(f"Transferred: {result}")
-```
+## 🏗️ Model Architecture
 
-## 📚 Supported Authors
+- **Base Model:** UBC-NLP/AraT5v2-base-1024
+- **Approach:** Descriptive Author Tokens + Prompt Engineering
+- **Input Format:** `"اكتب النص التالي بأسلوب <author:name>: [text]"`
+- **Training:** Fine-tuned with author-specific tokens
 
-1. يوسف إدريس
-2. نجيب محفوظ
-3. طه حسين
-4. حسن حنفي
-5. عبد الغفار مكاوي
-6. سلامة موسى
-7. أحمد شوقي
-8. أحمد تيمور باشا
-9. ثروت أباظة
-10. جبران خليل جبران
-11. روبرت بار
-12. ويليام شيكسبير
-13. أمين الريحاني
-14. غوستاف لوبون
-15. أحمد أمين
-16. محمد حسين هيكل
-17. جُرجي زيدان
-18. عباس محمود العقاد
-19. فؤاد زكريا
-20. كامل كيلاني
-21. نوال السعداوي
-
-## 🔧 Usage Examples
-
-### 1. Command Line Interface
-
-#### Interactive Mode
-```bash
-python inference_arabic_author_transfer.py --interactive
-```
+## 🔬 Technical Details
 
-#### Single Text Transfer
-```bash
-python inference_arabic_author_transfer.py \
-    --text "التعليم مهم جداً في حياتنا اليومية" \
-    --author "يوسف إدريس"
-```
+### Stylometric Analysis
+The model incorporates comprehensive stylometric analysis including:
+- **Lexical Features:** Sentence length, word length, vocabulary richness
+- **Syntactic Patterns:** Definite articles, conjunctions, prepositions
+- **Author-Specific Vocabulary:** TF-IDF based characteristic words
+- **Style Classification:** Formality, complexity, emotional intensity
 
-#### Batch Processing from File
-```bash
-python inference_arabic_author_transfer.py \
-    --input_file input.csv \
-    --output_file results.csv
-```
+### Prompt Engineering
+- **Format:** `"اكتب النص التالي بأسلوب <author:يوسف_إدريس>: [original_text]"`
+- **Author Tokens:** Descriptive tokens like `<author:يوسف_إدريس>`
+- **Target:** Generated text in author's style
 
-### 2. Python API
 
-#### Single Text Transfer
-```python
-from inference_arabic_author_transfer import ArabicAuthorTextTransfer
+## 🎯 Model Performance
 
-model = ArabicAuthorTextTransfer()
+- **BLEU Score:** 24.58
+- **chrF Score:** 59.01
+- **Competition:** First Place in AraGenEval 2024
+- **Supported Authors:** 21 Arabic authors
 
-# Transfer to single author
-result = model.transfer_style(
-    text="العلم نور والجهل ظلام",
-    target_author="نجيب محفوظ"
-)
-```
 
-#### Batch Processing
-```python
-texts = [
-    "الحياة جميلة",
-    "العلم أساس التقدم",
-    "الأدب غذاء الروح"
-]
-
-results = model.batch_transfer_style(
-    texts=texts,
-    target_author="أحمد شوقي",
-    batch_size=4
-)
-```
+## 📚 Supported Authors
 
-#### Get Supported Authors
-```python
-authors = model.get_supported_authors()
-print(f"Supported authors: {authors}")
-```
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/628f7a71dd993507cfcbe587/qDHUSa6ZvD1LjN9uJs-jp.png" width="600"/>
+</p>
 
-### 3. Advanced Parameters
-
-```python
-result = model.transfer_style(
-    text="النص الأصلي",
-    target_author="يوسف إدريس",
-    max_length=512,      # Maximum generation length
-    num_beams=5,         # Number of beams for beam search
-    temperature=1.0,     # Sampling temperature
-    do_sample=False      # Use deterministic generation
-)
-```
 
 ## 📁 Input File Format
 
@@ -153,34 +66,14 @@ For batch processing, your input file should have the following format:
 ### CSV Format
 ```csv
 text,author
-"التعليم مهم جداً في حياتنا اليومية","يوسف إدريس"
-"العلم نور والجهل ظلام","نجيب محفوظ"
-"الحياة جميلة","طه حسين"
-```
 
-### Excel Format
-Same structure as CSV but in Excel format.
 
-## 🏗️ Model Architecture
 
-- **Base Model:** UBC-NLP/AraT5v2-base-1024
-- **Approach:** Descriptive Author Tokens + Prompt Engineering
-- **Input Format:** `"اكتب النص التالي بأسلوب <author:name>: [text]"`
-- **Training:** Fine-tuned with author-specific tokens
 
-## 🔬 Technical Details
-
-### Stylometric Analysis
-The model incorporates comprehensive stylometric analysis including:
-- **Lexical Features:** Sentence length, word length, vocabulary richness
-- **Syntactic Patterns:** Definite articles, conjunctions, prepositions
-- **Author-Specific Vocabulary:** TF-IDF based characteristic words
-- **Style Classification:** Formality, complexity, emotional intensity
+```
 
-### Prompt Engineering
-- **Format:** `"اكتب النص التالي بأسلوب <author:يوسف_إدريس>: [original_text]"`
-- **Author Tokens:** Descriptive tokens like `<author:يوسف_إدريس>`
-- **Target:** Generated text in author's style
+### Excel Format
+Same structure as CSV but in Excel format.
 
 ## 📊 Performance Metrics
 
@@ -215,6 +108,18 @@ This model is released under the same license as the base AraT5v2 model.
 
 For questions about the model or usage, please refer to the competition documentation or model repository.
 
+
+## BibTeX Citation
+
+```bibtex
+@inproceedings{nacar2025anlpers,
+  title={ANLPers at AraGenEval Shared Task: Descriptive Author Tokens for Transparent Arabic Authorship Style Transfer},
+  author={Nacar, Omer and Reda, Mahmoud and Sibaee, Serry and Alhabashi, Yasser and Ammar, Adel and Boulila, Wadii},
+  booktitle={Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},
+  pages={49--53},
+  year={2025}
+}
+```
 ---
 
 **🏆 First Place Winner at AraGenEval 2025 - Arabic Text Style Transfer Competition**