This NLP task involves finding the part of the sentence that is responsible for neutral/ positive/ negative sentiment in the tweet.
Link to the dataset https://www.kaggle.com/c/tweet-sentiment-extraction/data
Roberta-base pretrained model - 0.715 jaccard score on test dataset. (see ipynb file for codes and outputs)
BerTweet pretrained model - 0.709 final jaccard score on test dataset. (see ipynb file for codes and outputs)