Detecting Discrepancies in Numeric Estimates Using Multidocument Hypertext Summaries

Michael White, Claire Cardie, Vincent Ng, and Daryl McCullough.
Second International Conference on Human Language Technology Research (HLT), 2002.

Click here for the PDF version.

Abstract

To aid analysts in detecting discrepancies in numeric estimates in news articles from multiple sources, we propose the automatic generation of hypertext summaries that include a high-level textual overview; tables of all comparable numeric estimates, organized to highlight discrepancies; and targeted access to supporting information from the original articles. The RIPTIDES system, which exemplifies the more flexible human-computer interface we propose, combines information extraction and multidocument summarization techniques to produce such hypertext summaries. In evaluating the system's ability to facilitate discrepancy detection, we find that, on average, the hypertext summaries provide a significantly more complete picture of the available information than the latest article.