Annexe A : Références de base
Domaine Références
Data mining (Han et Kamber 2006)
Désambiguïsation des toponymes (Leidner 2007)
Désambiguïsation des sens des mots (Ide et
Véronis 1998)
(Navigli 2009)
Informations géographiques et système et (Longley,
et al. 2005)
d'information géographique (Laurini 1996) (disponible dans
la
bibliothèque centrale de UMC)
Géo-référencement (Hill 2006)
Annexe B : Fonction de calcul de la Densité
Géographique écrite en Perl
sub geographical_density { @toponyms = ();
@toponyms = @_;
%tab_frequence = (); %topo_file = ();
foreach $topony (@toponyms)
{ @topo_hierars = ();
@topo_hierars = get_topo_hierar($topony);
@{$topo_file{$topony}}{@topo_hierars} = () x
@topo_hierars;
#@affich = keys %{$topo_file{$topony}};
#print "les hirar de $topony sont @affich \n";
@components = ();
@components = get_hierars_components(@topo_hierars); foreach $r
(@components)
{ $tab_frequence{$r}++; }
}
@tab f = ();
_
@tab_f = %tab_frequence;
foreach $topony (keys %topo_file) #reference to an
hierarchis
{ $ref_h = $topo_file{$topony};
@tab_hie =();
@tab_hie = keys %{$ref_h}; # retrieve hierarchis of a
toponym
foreach $h (@tab_hie)
{ @tab_h = ();
@tab_h = split (/>/,"$h");
$length_h = @tab_h; $topo_file{$topony}{$h}{"frequence"} =
referent_frequence($h,\%tab_frequence);
$topo_file{$topony}{$h}{"SC"} =
context_inter_score($h,\@toponyms);
$topo_file{$topony}{$h}{"length_h"} = $length_h; $topo_file{$topony}{$h}{"DG"}
=
$topo_file{$topony}{$h}{"frequence"} +
$topo_file{$topony}{$h}{"SC"};
}
}
return \%topo_file;}
Annexe C : Le toponyme ambigu `Georgia'
dans les fichiers de WordNet et le
corpus GeoSemCor
Data.noun 08889889 15 n 02 Georgia 1 Sakartvelo 0 008 @i
08578498
n 0000 #p 08401715 n 0000 #m 08181367 n 0000 + 03148509 a 0101 %p
08890235 n 0000 %p 08890396 n 0000 %p 08890614 n 0000 %m 09587708 n 0000 | a
republic in Asia Minor on the Black Sea separated from Russia by the Caucasus
mountains; formerly an Asian soviet but became independent in 1991
08945623 15 n 04 Georgia 0 Empire_State_of_the_South 0
Peach_State 0 GA 0 018 @i 08534691 n 0000 #p 08915715 n 0000 #m 08920565 n 0000
#m 08921379 n 0000 + 03148282 a 0101 -r 01266860 n 0000 %p 08946257 n 0000 %p
08946399 n 0000 %p 08946706 n 0000 %p 08946835 n 0000 %p 08947280 n 0000 %p
08947398 n 0000 %p 08947538 n 0000 %p 09109867 n 0000 %p 09123267 n 0000 %p
09148673 n 0000 %p 09243465 n 0000 %p 09318270 n 0000 | a state in southeastern
United States; one of the Confederate states during the American Civil War
08946145 15 n 01 Georgia 2 001 @i 08918800 n 0000 | one of the
British colonies that formed the United States
Index.noun georgia n 3 6 @ #m #p %m %p - 3 2 08512235 08512738
08459739
georgia n 3 7 @ #m #p %m %p + - 3 2 08945623 08946145 08889889
Index.sense georgia%1:15:00:: 08945623 1 17
georgia%1:15:01:: 08889889 3 0 georgia%1:15:02:: 08946145 2
1
GeoSemCor geosemcor2.0/brown1/tagfiles/br-a01:<wf geo=true
cmd=done pos=NN lemma=georgia wnsn=1
lexsn=1:15:00::>Georgia</wf>
geosemcor2.0/brown1/tagfiles/br-h01:<wf geo=true cmd=done
rdf=georgia pos=NN lemma=georgia wnsn=1 lexsn=1:15:00::>Ga.</wf>
geosemcor2.0/brown2/tagfiles/br-g17:<wf geo=true cmd=done
pos=NN lemma=georgia wnsn=2 lexsn=1:15:02::>Georgia</wf>
|