Using Rhetorical Topics for Automatic Summarization

Summarization involves finding the most important information in a text in order to convey the meaning of the document. In this paper, I present a method for using topic information to influence which content is selected for a summary. Texts are divided into topics using rhetorical information that creates a partition of a text into a sequence of non-overlapping topics. To investigate the effect of this topic structure, I compare the output of summarizing an entire text without topics to summarizing individual topics and combining them into a complete summary. The results show that the use of these rhetorical topics improves summarization performance compared to a summarization system that incorporates no topic information, demonstrating the utility of topic structure and rhetorical information for automatic summarization