Generic Sentence Fusion is an Ill-Defined Summarization Task

Abstract

We report on a series of human evaluations of the task of sentence fusion. In this task, a human is given two sentences and asked to produce a single coherent sentence that contains only the important information from the original two. Thus, this is a highly constrained summarization task. Our investigations show that even at this restricted level, there is no measurable agreement between humans regarding what information should be considered important. We further investigate the ability of separate evaluators to assess summaries, and find similarly disturbing lack of agreement.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2004
Accession Number
ADA461416

Entities

People

  • Daniel Marcu
  • Hal Daume Iii

Organizations

  • University of Southern California

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Agreements
  • Applied Computer Science
  • Automated Text Summarization
  • Computational Linguistics
  • Computational Science
  • Computer Programs
  • Computers
  • Hidden Markov Models
  • Information Science
  • Language
  • Linguistics
  • Machine Translation
  • Markov Models
  • Models
  • Natural Language Processing
  • Standards

Readers

  • Speech Processing/Speech Recognition.
  • Systems Analysis and Design