On macro- and micro-level information in multiple documents and its influence on summarization

Zhan, Jiaming, Loh, Han Tong and Liu, Ying ORCID: https://orcid.org/0000-0001-9319-5940 2009. On macro- and micro-level information in multiple documents and its influence on summarization. International Journal of Information Management 29 (1) , pp. 57-66. 10.1016/j.ijinfomgt.2008.04.011

Full text not available from this repository.

Abstract

A well-known challenge for multi-document summarization (MDS) is that a single best or “gold standard” summary does not exist, i.e. it is often difficult to secure a consensus among reference summaries written by different authors. It therefore motivates us to study what the “important information” is in multiple input documents that will guide different authors in writing a summary. In this paper, we propose the notions of macro- and micro-level information. Macro-level information refers to the salient topics shared among different input documents, while micro-level information consists of different sentences that act as elaborating or provide complementary details for those salient topics. Experimental studies were conducted to examine the influence of macro- and micro-level information on summarization and its evaluation. Results showed that human subjects highly relied on macro-level information when writing a summary. The length allowed for summaries is the leading factor that affects the summary agreement. Meanwhile, our summarization evaluation approach based on the proposed macro- and micro-structure information also suggested that micro-level information offered complementary details for macro-level information. We believe that both levels of information form the “important information” which affects the modeling and evaluation of automatic summarization systems.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Research Institutes & Centres > Centre for Advanced Manufacturing Systems At Cardiff (CAMSAC) Schools > Engineering
Subjects:	T Technology > TA Engineering (General). Civil engineering (General)
Uncontrolled Keywords:	Multi-document summarization; Document structure analysis; Summarization evaluation
Publisher:	Elsevier
ISSN:	0268-4012
Last Modified:	25 Oct 2022 07:59
URI:	https://orca.cardiff.ac.uk/id/eprint/51002

Citation Data

Cited 6 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item