Task-based evaluation of summary quality: Describing relationships between scientific papers

From AcaWiki
Jump to: navigation, search


Citation: Teufel, Simone (2001) Task-based evaluation of summary quality: Describing relationships between scientific papers. Workshop ``Automatic Summarization, NAACL-2001 (RSS)


Download: http://www.cl.cam.ac.uk/~sht25/papers/naacl01.pdf

Tagged: Computer Science (RSS) summarization (RSS), evaluation (RSS), information retrieval (RSS), computational linguistics (RSS), to improve (RSS)


Summary:

This paper concerns the task of determining how a scientific paper relates to previous work it describes and cites. It uses this task to evaluate summaries generated from based on the rhetorical status.

6 groups (with a total of 24 subjects) and 6 experiments were used, where each task was limited to 10 minutes to ensure completion in a 1 hour time frame.

This is part of the 'argumentation zoning' project of Simone Teufel's thesis. See also An annotation scheme for discourse-level argumentation in research articles (which introduces the zones), Discourse-level argumentation in scientific articles: Human and automatic annotation, and What's yours and what's mine: Determining intellectual attribution in scientific text.