• Title of article

    Abstraction Assistant: An automatic text abstraction system

  • Author/Authors

    Wendy Wang1، نويسنده , , Drew Hwang2، نويسنده ,

  • Issue Information
    ماهنامه با شماره پیاپی سال 2010
  • Pages
    10
  • From page
    1790
  • To page
    1799
  • Abstract
    In the interest of standardization and quality assurance, it is desirable for authors and staff of access services to follow the American National Standards Institute (ANSI) guidelines in preparing abstracts. Using the statistical approach an extraction system (the Abstraction Assistant) was developed to generate informative abstracts to meet the ANSI guidelines for structural content elements. The system performance is evaluated by comparing the system-generated abstracts with the authorʹs original abstracts and the manually enhanced system abstracts on three criteria: balance (satisfaction of the ANSI standards), fluency (text coherence), and understandability (clarity). The results suggest that it is possible to use the system output directly without manual modification, but there are issues that need to be addressed in further studies to make the system a better tool.
  • Journal title
    Journal of the American Society for Information Science and Technology
  • Serial Year
    2010
  • Journal title
    Journal of the American Society for Information Science and Technology
  • Record number

    994293