Interactive Abstractive Summarization for Event News Tweets
Ori Shapira, Hadar Ronen, Meni Adler, Yael Amsterdamer, Judit Bar‐Ilan, Ido Dagan · 2017
We present a novel interactive summarization system that is based on abstractive summarization, derived from a recent consolidated knowledge representation for multiple texts.We incorporate a couple of interaction mechanisms, providing a bullet-style summary while allowing to attain the most important information first and interactively drill down to more specific details.A usability study of our implementation, for event news tweets, suggests the utility of our approach for text exploration.