Summarization evaluation using relative utility

Dragomir R. Radev, Daniel Tam

Abstract: We present a series of experiments to demonstrate the validity of Relative Utility (RU) as a measure for evaluating extractive summarizers. RU is applicable in both single-document and multi-document summarization, is extendable to arbitrary compression rates with no extra annotation effort, and takes into account both random system performance and interjudge agreement. Our results using the JHU summary corpus indicate that RU is a reasonable and often superior alternative to several common evaluation metrics.