A Survey for Multi-Document Summarization

Abstract

Automatic Multi-Document summarization is still hard to realize. Under such circumstances, we believe, it is important to observe how humans are doing the same task, and look around for different strategies. We prepared 100 document sets similar to the ones used in the DUC multi-document summarization task. For each document set, several people prepared the following data and we conducted a survey. A) Free style summarization B) Sentence Extraction type summarization C) Axis (type of main topic) D) Table style summary In particular, we will describe the last two in detail, as these could lead to a new direction for multisummarization research.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2003
Accession Number
ADA460234

Entities

People

  • Chikashi Nobata
  • Satoshi Sekine

Organizations

  • New York University

Tags

Communities of Interest

  • Space
  • Weapons Technologies

DTIC Thesaurus Topics

  • Acquisition
  • Agreements
  • Applied Computer Science
  • Artificial Intelligence
  • Automated Text Summarization
  • Automatic
  • Chi Square Test
  • Computational Linguistics
  • Computer Science
  • Data Sets
  • Fresh Water
  • Language
  • Linguistics
  • Natural Language Processing
  • New York
  • South Korea
  • Surveys

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Computational Linguistics
  • Military History / Militaries and War Studies