Home

Teaser --> User journey with tweets, product reviews, customer service

Structure

1. Kaggle Challenge --> What was it about?
2. What are transformers and SimpleTransformers? Why are these important? (brief content)
3. Text extraction, question answering and sentiment extraction (transfer learning)
4. Tutorial
5. Advanced Techniques

• We used Huggingface pertained transformer models (Roberta-base-cased) and added customized question-answer head layers using TensorFlow to reach a better question answering result.
• Please see more details from this notebook Link to Tensorflow approach
• Key difference:

• TensorFlow approach can support more customized functions including customizing loss function, question answering structures, the number of inputs, and doing k-fold.
• TensorFlow approach can help you understand deeper on how transformers work by creating attention mask, input ids, and padding your train set.
• The training time takes longer for this approach as we are using the k-fold method to avoid overfitting

6. Key Insights
7. Lessons Learned and Best Practices
8. Resources