Multi-document summarization of dissertation abstracts using a variable-based framework

• Main Authors: Ou, Shiyan, Goh, Dion Hoe-Lian, Khoo, Christopher S. G.
• Other Authors: Wee Kim Wee School of Communication and Information
• Format: Conference or Workshop Item
• Language: English
• Published: 2010
• Subjects: DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval
• Online Access: https://hdl.handle.net/10356/91452; http://hdl.handle.net/10220/6197
• Institution: Nanyang Technological University

This paper reports initial work on developing a method for automatic construction of multi-document summaries of sets of domain-specific dissertation abstracts. A variable-based framework for multi-document summarization of dissertation abstracts in the field of sociology and psychology that makes use of the macro-level and micro-level discourse structure of dissertation abstracts as well as cross-document structure is proposed. The micro-level structure of problem statements found in a sample of 50 dissertation abstracts was analyzed, and the common features found are described. A list of indicator phrases that denote different aspects of the problem statements is provided.