A trainable document summarizer
Published 1 January 1995Open access
Julian Kupiec, Jan Pedersen, Francine Chen
Citations1,349
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The trends in the results are in agreement with those of Edmundson who used a subjectively weighted combination of features as opposed to training the feature weights using a corpus, which suggests that even shorter extracts may be useful indicative summmies.
Abstract
To summarize is to reduce in complexity, and hence in length, while retaining some of the essential qualities of the original.This paper focusses on document extracts, a particular kind of computed document summary.Document extracts consisting of roughly 20% of the original cart be as informative as the full text of a document, which suggests that even shorter extracts may be useful indicative summmies.The trends in our results are in agreement with those of Ed- mundson who used a subjectively weighted combination of features as opposed to training the feature weights using a corpus.We have developed a trainable summarization program that is grounded in a sound statistical framework.
Keywords
Computer Science
IBM Journal of Research and DevelopmentThe Automatic Creation of Literature Abstracts
3,211 Citations1958H. P. Luhn
In the exploratory research described, the complete text of an article in machine-readable form is scanned by an IBM 704 data-processing machine and analyzed in accordance with a standard program.
Journal of the ACMNew Methods in Automatic Extracting
1,469 Citations1969H. P. Edmundson
New methods of automatically extracting documents for screening purposes, i.e. the computer selection of sentences having the greatest potential for conveying to the reader the substance of the document, indicate that the three newly proposed components dominate the frequency component in the production of better extracts.
IBM Journal of Research and DevelopmentMachine-Made Index for Technical Literature—An Experiment
550 Citations1958P. B. Baxendale
It is shown that the coordinated index provided by the phrase is the more meaningful and discriminating.
Approaches to passage retrieval in full text information systems
387 Citations1993Gerard Salton, James Allan +1 more
New approaches are described in this study for implementing selective passage retrieval systems, and identifying text passages responsive to particular user needs.
Information Processing & ManagementConstructing literature abstracts by computer: Techniques and prospects
385 Citations1990Chris D. Paice
The question of how to achieve proper balance in auto-abstracts is a problem which has hardly been addressed hitherto; it appears that assignment of selected textual material into ‘abstract-frames’ may offer a solution.
ScienceAutomatic Analysis, Theme Generation, and Summarization of Machine-Readable Texts
270 Citations1994Gerard Salton, James Allan +2 more
Methods are given for determining text themes, traversing texts selectively, and extracting summary statements that reflect text content in arbitrary subject areas in accordance with user needs.
Communications of the ACMSCISOR: extracting information from on-line news
217 Citations1990Paul S. Jacobs, Lisa F. Rau
The future of natural language text processing is examined in the SCISOR prototype, drawing on artificial intelligence techniques, and applying them to financial news items through a combination of bottom-up and top-down processing.
The identification of important concepts in highly structured technical papers
150 Citations1993Chris D. Paice, Paul A. Jones
This paper describes an approach in which the indexing and abstracting tasks are effectively combined, applicable to highly structured empirical research papers, whose content can be organised using a semantic frame.
American DocumentationThe formation of abstracts by the selection of sentences. Part I. Sentence selection by men and machines
115 Citations1961Gitika Rath, A. Resnick +1 more
There was very little agreement between the subjects and machine methods in their selection of representative sentences, and human selection of sentences is considerably more variable than the machine methods.
Information Systems ResearchThe Effects and Limitations of Automated Text Condensing on Reading Comprehension Performance
113 Citations1992Andrew H. Morris, George M. Kasper +1 more
It is suggested that it is possible to apply a relatively simple computer algorithm to text and produce extracts that capture enough of the information contained in the original document so that the recipient can perform as if he or she had read the original.
The use of emphasis to automatically summarize a spoken discourse
76 Citations1992F.R. Chen, M. Withgott
The authors describe a method for exploiting prosodic information in natural, conventional speed for the purpose of automatically creating an audio summary based on identifying emphasized speech and then using proximity measures on the emphasized regions to select summarizing excerpts.
Text condensation as knowledge base abstraction
54 Citations2003Ulrich Reimer, Udo Hahn
A model of knowledge-based text condensation is presented which has been implemented as part of the text information system TOPIC and supports variable degrees of abstraction for text summarization as well as content-oriented retrieval of text knowledge.
Automatic Analysis, Theme Generation, and Summarization of Machine-Readable Texts
36 Citations1996Gerard Salton, James Allan +2 more
Information Processing & ManagementContent based text handling
30 Citations1990Christoph Schwarz
Research and development in the field of content based text handling at the Siemens Corporate Research Laboratories are described in this article.