From discourse structures to text summaries 论文

摘要

We describe experiments that show that the concepts of rhetorical analysis and nuclearity can be used effectively for determining the most important units in a text. We show how these concepts can be implemented and we discuss results that we obtained with a discourse-based summarization program. 1 Motivation The evaluation of automatic summarizers has always been a thorny problem: most papers on summarization describe the approach that they use and give some "convincing " samples of the output. In very few cases, the direct output of a summarization program is compared with a human-made summary or evaluated with the help of human subjects; usually, the results are modest. Unfortunately, evaluating the results of a particular implementation does not enable one to determine what part of the failure is due to the implementation itself and what part to its underlying assumptions. The position that we take in this paper is that, in order to build high-quality summarization programs, one ...