H. Luhn. IBM Journal of Research and Development, 2 (2):
159--165(1958)
Abstract
Excerpts of technical papers and magazine articles that serve the purposes of conventional abstracts have been created entirely by automatic means. 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. Statistical information derived from word frequency and distribution is used by the machine to compute a relative measure of significance, first for individual words and then for sentences. Sentences scoring highest in significance are extracted and printed out to become the äuto-abstract."
Description
Excerpts of technical papers and magazine articles that serve the purposes of conventional abstracts have been created entirely by automatic means. 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. Statistical information derived from word frequency and distribution is used by the machine to compute a relative measure of significance, first for individual words and then for sentences. Sentences scoring highest in significance are extracted and printed out to become the "auto-abstract."
%0 Journal Article
%1 textmining1958
%A Luhn, H. P.
%D 1958
%J IBM Journal of Research and Development
%K 1958 IBM abstracts automatic creation literature mining text wismasys0809
%N 2
%P 159--165
%T The Automatic Creation of Literature Abstracts
%U http://www.research.ibm.com/journal/rd/022/luhn.pdf
%V 2
%X Excerpts of technical papers and magazine articles that serve the purposes of conventional abstracts have been created entirely by automatic means. 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. Statistical information derived from word frequency and distribution is used by the machine to compute a relative measure of significance, first for individual words and then for sentences. Sentences scoring highest in significance are extracted and printed out to become the äuto-abstract."
@article{textmining1958,
abstract = {Excerpts of technical papers and magazine articles that serve the purposes of conventional abstracts have been created entirely by automatic means. 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. Statistical information derived from word frequency and distribution is used by the machine to compute a relative measure of significance, first for individual words and then for sentences. Sentences scoring highest in significance are extracted and printed out to become the "auto-abstract."},
added-at = {2010-01-13T10:08:06.000+0100},
author = {Luhn, H. P.},
biburl = {https://www.bibsonomy.org/bibtex/245d22ece3ed303ba91ae15e8b50f9a81/praveen},
description = {Excerpts of technical papers and magazine articles that serve the purposes of conventional abstracts have been created entirely by automatic means. 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. Statistical information derived from word frequency and distribution is used by the machine to compute a relative measure of significance, first for individual words and then for sentences. Sentences scoring highest in significance are extracted and printed out to become the "auto-abstract."},
interhash = {46e7437dc92fc2f94b19b31d0dbe9758},
intrahash = {45d22ece3ed303ba91ae15e8b50f9a81},
journal = {IBM Journal of Research and Development},
keywords = {1958 IBM abstracts automatic creation literature mining text wismasys0809},
number = 2,
pages = {159--165},
timestamp = {2010-01-13T10:08:07.000+0100},
title = {The Automatic Creation of Literature Abstracts},
url = {http://www.research.ibm.com/journal/rd/022/luhn.pdf},
volume = 2,
year = 1958
}