Query-biased summarization considering difference of paragraphs

Chikara Otani*, Moon Kyeng Hoo, Yasushi Oda, Toshihiko Furue, Yoshitaka Uchida, Osamu Yoshie

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)


Most existing query-biased summarization methods generate the summary using extracted sentences based on similarity measure between all sentences in documents and the query. If there are plural sentences having high similarity to the query in the documents, however, these methods cannot decide from which sentence the summary should be made. This paper proposes an algorithm considering difference of paragraphs, adopting new indicator that shows the difference between one paragraph and the others. In a word space composed of all words in the target document, the algorithm determines the axis that maximizes the difference when a paragraph and the others are projected onto it. There are many combinations of a paragraph and a set of other paragraphs. For each combination, the above-mentioned axis that maximizes the difference and gives a conformity degree to the given query is calculated. With these conformities, the algorithm decides one paragraph for generating the summary. To obtain the axes, topic distinctiveness factor analysis is applied. The basic idea for making final summary is concatenating the sentences extracted from the paragraph. The resultant summary is evaluated from the points of readability, understandability and the easiness to judge whether the link works well or not.

Original languageEnglish
Pages (from-to)2256-2265+21
JournalIEEJ Transactions on Electronics, Information and Systems
Issue number12
Publication statusPublished - 2010


  • Information search
  • Query-biased summarization
  • Topic distinctiveness factor analysis

ASJC Scopus subject areas

  • Electrical and Electronic Engineering


Dive into the research topics of 'Query-biased summarization considering difference of paragraphs'. Together they form a unique fingerprint.

Cite this