T5-Small Shakespeare Q&A Model

A fine-tuned T5-small model specialized for answering questions about William Shakespeare's plays and works. This model has been trained on a comprehensive dataset of Shakespeare-related questions and answers.

🎭 Model Description

• Base Model: google/t5-small (60M parameters)
• Task: Question Answering about Shakespeare's literary works
• Training: Fine-tuned on custom Shakespeare Q&A dataset
• Language: English
• License: Apache 2.0

🚀 Quick Start

from transformers import T5ForConditionalGeneration, T5Tokenizer

# Load model and tokenizer
model_name = "Hananguyen12/T5-Small-QA-Shakespeare"
tokenizer = T5Tokenizer.from_pretrained(model_name)
model = T5ForConditionalGeneration.from_pretrained(model_name)

# Ask a question (use "factual: " prefix)
question = "factual: Who is the protagonist in Hamlet?"
inputs = tokenizer(question, return_tensors="pt", max_length=512, truncation=True)

# Generate answer
outputs = model.generate(
    **inputs,
    max_length=256,
    num_beams=4,
    early_stopping=True,
    temperature=0.7
)

answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(f"Q: {question.replace('factual: ', '')}")
print(f"A: {answer}")

📚 Supported Topics

This model can answer questions about:

• Characters: Main and supporting characters across all plays
• Plots: Story summaries, key events, and plot points
• Themes: Major themes and literary analysis
• Settings: Time periods and locations of plays
• Quotes: Famous lines and speeches (context)
• Historical Context: Shakespeare's life and times

🎯 Usage Tips

1. Prefix Format: Always use "factual: " before your question for best results
2. Question Types: Works best with factual, direct questions
3. Specificity: More specific questions yield better answers
4. Play Names: You can ask about any of Shakespeare's major works

📖 Example Interactions

Input: "factual: What happens to Romeo and Juliet at the end?"
Output: "Romeo and Juliet both die by suicide - Romeo drinks poison and Juliet stabs herself with Romeo's dagger."

Input: "factual: Who are the three witches in Macbeth?"
Output: "The three witches are supernatural beings who prophesy Macbeth's rise to power and influence the tragic events of the play."

Input: "factual: What is the setting of A Midsummer Night's Dream?"
Output: "A Midsummer Night's Dream is set in Athens and the nearby enchanted forest, during ancient Greek times."

⚙️ Technical Details

• Architecture: T5 (Text-to-Text Transfer Transformer)
• Model Size: ~60M parameters
• Max Input Length: 512 tokens
• Max Output Length: 256 tokens
• Training Epochs: 20
• Learning Rate: 3e-4
• Batch Size: 8

🎓 Educational Applications

Perfect for:

• Literature education chatbots
• Shakespeare study assistants
• Interactive learning platforms
• Educational Q&A systems
• Student research tools

⚠️ Limitations

• Specialized only for Shakespeare's works
• Best with factual questions (not creative interpretation)
• Requires "factual: " prefix for optimal performance
• May not handle very complex literary analysis questions

📄 Citation

@misc{shakespeare-qa-t5,
  title={T5-Small Shakespeare Q&A Model},
  author={Hananguyen12},
  year={2025},
  url={https://huggingface.co/Hananguyen12/T5-Small-QA-Shakespeare}
}

🔗 Links

• Model Repository: https://huggingface.co/Hananguyen12/T5-Small-QA-Shakespeare
• Base Model: https://huggingface.co/google/t5-small
• Framework: Hugging Face Transformers

---

Fine-tuned with ❤️ for Shakespeare education and literature learning