Skip to main content
. Author manuscript; available in PMC: 2021 Jun 24.
Published in final edited form as: Proc Conf. 2021 Jun;2021:4794–4811. doi: 10.18653/v1/2021.naacl-main.382

Figure 2:

Figure 2:

We plot average ROUGE score as summaries are greedily built by adding the sentence with the highest relative ROUGE gain vis-a-vis the current summary, until the gain is no longer positive (ORACLE GAIN). We also include the difference between the highest scoring sentence and the average / minimum to demonstrate a weakening sentence selection signal after the top 1–2.