We show that generating English Wikipedia articles can be approached as a multi- document summarization of source documents.
There is thus a crucial gap between sentence selection and fusion to support summarizing by both compressing single sentences and fusing pairs.
Generating a text abstract from a set of documents remains a challenging task.
Compared to the state-of-the-art unsupervised evaluation metrics, SUPERT correlates better with human ratings by 18-39%.
In this paper, we propose GameWikiSum, a new domain-specific dataset for multi-document summarization, which is one hundred times larger than commonly used datasets, and in another domain than news.
Extracting summaries via integer linear programming and submodularity are popular and successful techniques in extractive multi-document summarization.