Systematically Exploring Redundancy Reduction in Summarizing Long Documents
This work tackles the problem of redundancy in long document summarization, which is a common issue for researchers and practitioners working with large text datasets. It offers an incremental improvement by systematically exploring and proposing new methods within existing categories.
This paper addresses the significant problem of redundancy in summarizing long documents, which is prevalent in large summarization datasets. The authors propose three new methods that balance non-redundancy and importance, achieving state-of-the-art ROUGE scores on the Pubmed and arXiv datasets while substantially reducing redundancy.
Our analysis of large summarization datasets indicates that redundancy is a very serious problem when summarizing long documents. Yet, redundancy reduction has not been thoroughly investigated in neural summarization. In this work, we systematically explore and compare different ways to deal with redundancy when summarizing long documents. Specifically, we organize the existing methods into categories based on when and how the redundancy is considered. Then, in the context of these categories, we propose three additional methods balancing non-redundancy and importance in a general and flexible way. In a series of experiments, we show that our proposed methods achieve the state-of-the-art with respect to ROUGE scores on two scientific paper datasets, Pubmed and arXiv, while reducing redundancy significantly.