Upload turk_tokenizer/data/turkish_proper_nouns.txt with huggingface_hub
Browse files
turk_tokenizer/data/turkish_proper_nouns.txt
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Turkish provinces (81 il) and major place names — lowercase
|
| 2 |
+
adana
|
| 3 |
+
adıyaman
|
| 4 |
+
afyonkarahisar
|
| 5 |
+
ağrı
|
| 6 |
+
aksaray
|
| 7 |
+
amasya
|
| 8 |
+
ankara
|
| 9 |
+
antalya
|
| 10 |
+
ardahan
|
| 11 |
+
artvin
|
| 12 |
+
aydın
|
| 13 |
+
balıkesir
|
| 14 |
+
bartın
|
| 15 |
+
batman
|
| 16 |
+
bayburt
|
| 17 |
+
bilecik
|
| 18 |
+
bingöl
|
| 19 |
+
bitlis
|
| 20 |
+
bolu
|
| 21 |
+
burdur
|
| 22 |
+
bursa
|
| 23 |
+
çanakkale
|
| 24 |
+
çankırı
|
| 25 |
+
çorum
|
| 26 |
+
denizli
|
| 27 |
+
diyarbakır
|
| 28 |
+
düzce
|
| 29 |
+
edirne
|
| 30 |
+
elazığ
|
| 31 |
+
erzincan
|
| 32 |
+
erzurum
|
| 33 |
+
eskişehir
|
| 34 |
+
gaziantep
|
| 35 |
+
giresun
|
| 36 |
+
gümüşhane
|
| 37 |
+
hakkari
|
| 38 |
+
hatay
|
| 39 |
+
ığdır
|
| 40 |
+
ısparta
|
| 41 |
+
istanbul
|
| 42 |
+
izmir
|
| 43 |
+
kahramanmaraş
|
| 44 |
+
karabük
|
| 45 |
+
karaman
|
| 46 |
+
kars
|
| 47 |
+
kastamonu
|
| 48 |
+
kayseri
|
| 49 |
+
kırıkkale
|
| 50 |
+
kırklareli
|
| 51 |
+
kırşehir
|
| 52 |
+
kilis
|
| 53 |
+
kocaeli
|
| 54 |
+
konya
|
| 55 |
+
kütahya
|
| 56 |
+
malatya
|
| 57 |
+
manisa
|
| 58 |
+
mardin
|
| 59 |
+
mersin
|
| 60 |
+
muğla
|
| 61 |
+
muş
|
| 62 |
+
nevşehir
|
| 63 |
+
niğde
|
| 64 |
+
ordu
|
| 65 |
+
osmaniye
|
| 66 |
+
rize
|
| 67 |
+
sakarya
|
| 68 |
+
samsun
|
| 69 |
+
siirt
|
| 70 |
+
sinop
|
| 71 |
+
sivas
|
| 72 |
+
şanlıurfa
|
| 73 |
+
şırnak
|
| 74 |
+
tekirdağ
|
| 75 |
+
tokat
|
| 76 |
+
trabzon
|
| 77 |
+
tunceli
|
| 78 |
+
uşak
|
| 79 |
+
van
|
| 80 |
+
yalova
|
| 81 |
+
yozgat
|
| 82 |
+
zonguldak
|
| 83 |
+
# Common Turkish district / region names
|
| 84 |
+
anadolu
|
| 85 |
+
trakya
|
| 86 |
+
karadeniz
|
| 87 |
+
ege
|
| 88 |
+
marmara
|
| 89 |
+
akdeniz
|
| 90 |
+
doğu
|
| 91 |
+
batı
|