Latent Semantic Analysis is used as a technique for measuring the coherence of texts. By comparing the vectors for two adjoining segments of text in a highdimensional semantic space, the method provides a characterization of the degree of semantic relatedness between the segments. We illustrate the approach for predicting coherence through re-analyzing sets of texts from two studies that manipulated the coherence of texts and assessed readers' comprehension. The results indicate that the method ...
%0 Journal Article
%1 citeulike:896217
%A Foltz, P.
%A Kintsch, W.
%A Landauer, T.
%D 1998
%J Discourse Processes
%K lsa text nlp coherence
%N 2&3
%P 285--307
%T The measurement of textual coherence with latent semantic analysis
%U http://citeseer.ist.psu.edu/foltz98measurement.html
%V 25
%X Latent Semantic Analysis is used as a technique for measuring the coherence of texts. By comparing the vectors for two adjoining segments of text in a highdimensional semantic space, the method provides a characterization of the degree of semantic relatedness between the segments. We illustrate the approach for predicting coherence through re-analyzing sets of texts from two studies that manipulated the coherence of texts and assessed readers' comprehension. The results indicate that the method ...
@article{citeulike:896217,
abstract = {Latent Semantic Analysis is used as a technique for measuring the coherence of texts. By comparing the vectors for two adjoining segments of text in a highdimensional semantic space, the method provides a characterization of the degree of semantic relatedness between the segments. We illustrate the approach for predicting coherence through re-analyzing sets of texts from two studies that manipulated the coherence of texts and assessed readers' comprehension. The results indicate that the method ...},
added-at = {2006-10-19T17:52:23.000+0200},
author = {Foltz, P. and Kintsch, W. and Landauer, T.},
biburl = {https://www.bibsonomy.org/bibtex/2b02a429d050d7affdc0e92f8354452ae/gridinoc},
citeulike-article-id = {896217},
interhash = {b14825a13fcbd18c5099d25df7ed3e20},
intrahash = {b02a429d050d7affdc0e92f8354452ae},
journal = {Discourse Processes},
keywords = {lsa text nlp coherence},
number = {2\&3},
pages = {285--307},
priority = {2},
timestamp = {2006-10-19T17:52:23.000+0200},
title = {The measurement of textual coherence with latent semantic analysis},
url = {http://citeseer.ist.psu.edu/foltz98measurement.html},
volume = 25,
year = 1998
}