Eigen-analysis such as LSI or KCCA was
already successfully applied to cross-lingual
information retrieval. This approach has a
weakness in that it needs an aligned training
set of documents. In this paper we address
this weakness and show that it can be successfully
avoided through the use of machine
translation. We show that the performance is
similar on the domains where human generated
training seta are available. However for
other domains artificial training sets can be
generated that significantly outperform human
generated ones obtained from a different
domain.
%0 Generic
%1 fortuna2005machine
%A Fortuna, Blaz
%A Shawe-Taylor, John
%D 2005
%K machine translation
%T The use of machine translation tools for cross-lingual text mining
%U http://eprints.pascal-network.org/archive/00001208/
%X Eigen-analysis such as LSI or KCCA was
already successfully applied to cross-lingual
information retrieval. This approach has a
weakness in that it needs an aligned training
set of documents. In this paper we address
this weakness and show that it can be successfully
avoided through the use of machine
translation. We show that the performance is
similar on the domains where human generated
training seta are available. However for
other domains artificial training sets can be
generated that significantly outperform human
generated ones obtained from a different
domain.
@misc{fortuna2005machine,
abstract = {Eigen-analysis such as LSI or KCCA was
already successfully applied to cross-lingual
information retrieval. This approach has a
weakness in that it needs an aligned training
set of documents. In this paper we address
this weakness and show that it can be successfully
avoided through the use of machine
translation. We show that the performance is
similar on the domains where human generated
training seta are available. However for
other domains artificial training sets can be
generated that significantly outperform human
generated ones obtained from a different
domain.},
added-at = {2014-03-13T11:50:00.000+0100},
author = {Fortuna, Blaz and Shawe-Taylor, John},
biburl = {https://www.bibsonomy.org/bibtex/25c48336baa1ae0323ce1cd59cde79f83/langlois},
description = {PASCAL -},
id = {http://eprints.pascal-network.org/archive/00001208/},
interhash = {4cda4d6ba6756f4326b96bf80b6dce1c},
intrahash = {5c48336baa1ae0323ce1cd59cde79f83},
keywords = {machine translation},
timestamp = {2014-03-13T11:50:00.000+0100},
title = {The use of machine translation tools for cross-lingual text mining},
type = {Conference or Workshop Item, PeerReviewed},
url = {http://eprints.pascal-network.org/archive/00001208/},
year = 2005
}