Generating Indicative-Informative Summaries with SumUM
- 1 December 2002
- journal article
- Published by MIT Press in Computational Linguistics
- Vol. 28 (4), 497-526
- https://doi.org/10.1162/089120102762671963
Abstract
We present and evaluate SumUM, a text summarization system that takes a raw technical text as input and produces an indicative informative summary. The indicative part of the summary identifies the topics of the document, and the informative part elaborates on some of these topics according to the reader's interest. SumUM motivates the topics, describes entities, and defines concepts. It is a first step for exploring the issue of dynamic summarization. This is accomplished through a process of shallow syntactic and semantic analysis, concept identification, and text regeneration. Our method was developed through the study of a corpus of abstracts written by professional abstractors. Relying on human judgment, we have evaluated indicativeness, informativeness, and text acceptability of the automatic summaries. The results thus far indicate good performance when compared with other summarization technologies.Keywords
This publication has 15 references indexed in Scilit:
- Searching the InternetIEEE Internet Computing, 1998
- Automatic abstracting researchLibrary Review, 1995
- Automatic condensation of electronic publications by sentence selectionInformation Processing & Management, 1995
- On abstract writingText & Talk - An Interdisciplinary Journal of Language, Discourse & Communication Studies, 1994
- Topic parsing: Accounting for text macro structures in full-text analysisInformation Processing & Management, 1990
- Knowledge-based abstractingOnline Review, 1990
- Some computational experiments in summarizationDiscourse Processes, 1990
- Plot Units and Narrative Summarization*Cognitive Science, 1981
- Comment on se rappelle et on résume des histoiresLangages, 1975
- New Methods in Automatic ExtractingJournal of the ACM, 1969