Speaker(s): Philippe Laban
Host: Royal Sequiera
Find the recording, slides, and more info at [ Ссылка ]
Motivation / Abstract
- This work presents a new approach to unsupervised abstractive summarization.
- At the time of writing Summary Loop outperforms previous unsupervised methods by more that 2 ROUGE-1 points
- The code is publicly available and the authors will also be demoing their ACL work on building a chatbot for the News domain
What was discussed?
What are the key takeaways?
------
#AISC hosts 3-5 live sessions like this on various AI research, engineering, and product topics every week! Visit [ Ссылка ] for more details
