Interactive Document Summarisation Using Automatically Extracted Keyphrases

This paper describes the Interactive Document Summariser (IDS). IDS provides dynamic control over document summary characteristics, such as length and topicfocus, so that changesmadeby the user are instantly reflected in an on-screensummay. ‘Summay-in-context’ viewsallow usersto moveflexibly betweensummariesand their source documents. IDS adopts the technique of sentence extraction, exploiting keyphrases that are automatically extractedfrom documenttext as theprimary attribute of a sentenceextraction algorithm. Wereport an evaluation of IDS summaries,in which representativeendusers of on-line documents identified relevant summary sentencesin source documents.IDS summarieswere then compared to the recommendations of the users and we report the efficacy of the summaries based on standard precision and recall measures. In addition, using established evaluation metrics we found that IDS summarieswere better than baselinesummariesbasedon within-documentsentenceordering.

• Type: Conference
• Year: 2002
• Where: HICSS
• Authors: Steve Jones, Stephen Lundy, Gordon W. Paynter
• Keywords: Biometrics, Document Summary Characteristics, HICSS 2002, Interactive Document Summariser, Summary Sentencesin Source