My attempt at the Tweet sentiment extraction Kaggle competition using BERT. Link to my submission: Kaggle notebook
- Fine-tuned several BERT models and other NLP transformers like XLNet, RoBERTa in a question-answer format to extract the substring of a given tweet which represents the given emotion of the tweet.
- Achieved a Jaccard similarity score of 0.687, better than around 600 other submissions.
- Programmed in Python and utilized PyTorch, transformers, Pandas, and Jupyter notebooks.