Because computers don't understand the meanings of words and sentences, automating the seemingly simple task of summarizing a news story using several sources is a major computer science challenge. Key to meeting the challenge is finding a way to identify the most important sentences from a set of documents on the same subject. Researchers from the University of Michigan have developed a multi-document summarization technique that compares sentences and has the effect of sentences voting for the most important among them. The method, dubbed LexRank, combines the content-sorting concepts of prestige and lexical similarity to find the most important sentences in a group of documents on the same subject. This has been added to Artificial Intelligence Resources Subject Tracer™ Information Blog.
posted by Marcus Zillman |
4:10 AM
