Home

Emotion Extraction using simple transformers

This project was completed as part of Kaggle competition in June 2020 (https://www.kaggle.com/c/tweet-sentiment-extraction). This project involved extracting emotions from Tweets. Our team submitted this git hub project to kaggle, we scored in 1000 :). We hope that it will help you get a jump start on sentiment extraction!

Our code is largely based on the simple transformer work done by: xxx here http://google.com

• NLP is important business applications
• emotion analysis -> emotion extraction
• transformers
• social media data
• provide insights to business

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

Topics to be completed in the future:

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