Comparative Evaluation of Term-Weighting Methods for Automatic Summarization*

Abstract

Term-based summarization assumes that it is possible to determine the importance of a sentence on the basis of the words it contains. To achieve this, words are weighted using term-weighting measures which in turn are used to weight the sentences. This article presents a comparative evaluation of summaries produced using different term-weighting measures and different combinations of parameters which are used to calculate these measures. Comparative evaluation of summaries produced reveals that in many cases simple methods such as term frequency can produce informative summaries.

Notes

¹This figure includes books, newspapers, scholarly journals, office documents, etc.

²The program is available at http://sourceforge.net/projects/jwordnet

³Because term frequency does not require any reference collection to be calculated, none of the summaries produced with term frequency were considered here.

⁴Chris Paice, personal communication.

⁵More information about these conferences can be found at http://duc.nist.gov