What is it about?
\emph{public opinion on a variety of issues fluctuates over time, creating historically shifting contexts.}. The historical context is a representation of how something occurs or is created and how it influences how we perceive it now as human compared to the past. So, our general research question is how can we keep our models updated with evolving vocabulary and knowledge so that we can keep up performance while minimising the human effort of labelling new data? What tools can help in this case?}
Featured Image
Photo by Agê Barros on Unsplash
Why is it important?
Our goal to to allow our model to leverage old annotated dataset without losing annotation effort or changing the contextual meaning encoded in the temporal embedding.
Read the Original
This page is a summary of: Opinions are Made to be Changed, August 2021, ACM (Association for Computing Machinery),
DOI: 10.1145/3472720.3483620.
You can read the full text:
Contributors
The following have contributed to this page
