Abstract

Hierarchies provide a means of organizing, summarizing and accessing information. We describe a method for automatically generating hierarchies from small collections of text, and then apply this technique to summarizing the documents retrieved by a search engine. We show that these hierarchies provide better access to the documents than a simple ranked list and that the terms in the hierarchy are better summaries of the documents than the top TF.IDF weighted terms. In addition, we discuss the formal framework of the technique and how the technique has been used with news databases and TREC collections.

Citations