Skip to content

HargovindArora/Assessing_the_Funniness_of_Edited_News_Headlines

Repository files navigation

Assessing_the_Funniness_of_Edited_News_Headlines

  • This project aimed at evaluating the effects of making short edits on a text, like news headlines and, does this short modification make the text more humourous, i.e. from non-funny to funny.
  • Project made using standard BERT transformer, made available through HuggingFace ibrary.
  • This was a regression task and an RMSE of 0.57 was obtained.
  • It is slightly above the base line score.
  • A lot more samples and restructuring of the data is required to obtain a low RMSE score, as this task is quite tricky.

About

Using Transformer for Regression tasks (scoring) in NLP

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published