540 lines
14 KiB
YAML
540 lines
14 KiB
YAML
# sl.yaml
|
|
# -------
|
|
# Slovenian language specification
|
|
|
|
components:
|
|
level:
|
|
null_probability: 0.9
|
|
alphanumeric_probability: 0.1
|
|
|
|
staircase:
|
|
null_probability: 0.99
|
|
alphanumeric_probability: 0.01
|
|
|
|
entrance:
|
|
null_probability: 0.999
|
|
alphanumeric_probability: 0.001
|
|
|
|
unit:
|
|
null_probability: 0.7
|
|
alphanumeric_probability: 0.3
|
|
|
|
combinations:
|
|
-
|
|
components:
|
|
- house_number
|
|
- staircase
|
|
- level
|
|
- unit
|
|
label: house_number
|
|
separators:
|
|
- separator: "/"
|
|
probability: 0.95
|
|
- separator: "-"
|
|
probability: 0.05
|
|
probability: 0.005
|
|
-
|
|
components:
|
|
- house_number
|
|
- level
|
|
- unit
|
|
label: house_number
|
|
separators:
|
|
- separator: "/"
|
|
probability: 0.95
|
|
- separator: "-"
|
|
probability: 0.05
|
|
probability: 0.005
|
|
-
|
|
components:
|
|
- house_number
|
|
- level
|
|
label: house_number
|
|
separators:
|
|
- separator: "/"
|
|
probability: 0.95
|
|
- separator: "-"
|
|
probability: 0.05
|
|
probability: 0.1
|
|
# For unit types like 2/34
|
|
-
|
|
components:
|
|
- house_number
|
|
- unit
|
|
label: house_number
|
|
separators:
|
|
- separator: "/"
|
|
probability: 0.95
|
|
- separator: "-"
|
|
probability: 0.05
|
|
probability: 0.005
|
|
|
|
|
|
numbers:
|
|
no_number:
|
|
default:
|
|
canonical: brez številke
|
|
abbreviated: brez št
|
|
sample: true
|
|
canonical_probability: 0.5
|
|
abbreviated_probability: 0.3
|
|
sample_probability: 0.2
|
|
|
|
default: &stevilke
|
|
canonical: številke
|
|
abbreviated: št
|
|
sample: true
|
|
canonical_probability: 0.3
|
|
abbreviated_probability: 0.6
|
|
sample_probability: 0.1
|
|
numeric:
|
|
direction: left
|
|
numeric_affix:
|
|
affix: "št."
|
|
whitespace_probability: 0.6
|
|
direction: left
|
|
numeric_probability: 0.6
|
|
numeric_affix_probability: 0.4
|
|
|
|
alphanumeric_phrase_probability: 0.05
|
|
no_number_probability: 0.05
|
|
|
|
|
|
and:
|
|
default: &in
|
|
canonical: in
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
|
|
|
|
cross_streets:
|
|
i: *in
|
|
at: &na
|
|
canonical: na
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
corner: &vogalu
|
|
canonical: vogalu
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
na_vogalu: &na_vogalu
|
|
canonical: na vogalu
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
intersection:
|
|
default: *in
|
|
probability: 0.7
|
|
alternatives:
|
|
- alternative: *na
|
|
probability: 0.1
|
|
- alternative: *vogalu
|
|
probability: 0.15
|
|
- alternative: *na_vogalu
|
|
probability: 0.05
|
|
|
|
med: &med
|
|
canonical: med
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
parentheses_probability: 0.5
|
|
between:
|
|
default: *med
|
|
|
|
levels:
|
|
nadstropje: &nadstropje
|
|
canonical: nadstropje
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
direction_probability: 0.9
|
|
digits:
|
|
ascii_probability: 0.7
|
|
roman_numeral_probability: 0.3
|
|
add_number_phrase: true
|
|
add_number_phrase_probability: 0.1
|
|
ordinal:
|
|
direction: right
|
|
digits:
|
|
ascii_probability: 0.3
|
|
roman_numeral_probability: 0.7
|
|
add_number_phrase: true
|
|
add_number_phrase_probability: 0.1
|
|
numeric_probability: 0.4
|
|
ordinal_probability: 0.6
|
|
|
|
pritlicje: &pritlicje
|
|
canonical: pritličje
|
|
sample: true
|
|
canonical_probability: 0.9
|
|
sample_probability: 0.1
|
|
parter: &parter
|
|
canonical: parter
|
|
sample: true
|
|
canonical_probability: 0.9
|
|
sample_probability: 0.1
|
|
kleti: &kleti
|
|
canonical: kleti
|
|
sample: true
|
|
canonical_probability: 0.7
|
|
sample_probability: 0.3
|
|
# e.g. kleti 1
|
|
numeric:
|
|
direction: left
|
|
direction_probability: 0.8
|
|
# e.g. 1. kleti
|
|
ordinal:
|
|
direction: right
|
|
digits:
|
|
ascii_probability: 0.7
|
|
roman_numeral_probability: 0.3
|
|
standalone_probability: 0.99
|
|
number_abs_value: true
|
|
number_min_abs_value: 1
|
|
numeric_probability: 0.005
|
|
ordinal_probability: 0.005
|
|
|
|
aliases:
|
|
"<-1":
|
|
default: *kleti
|
|
"-1":
|
|
default: *kleti
|
|
"0":
|
|
default: *pritlicje
|
|
probability: 0.5
|
|
alternatives:
|
|
- alternative: *parter
|
|
probability: 0.4
|
|
- alternative: *nadstropje
|
|
probability: 0.1
|
|
|
|
numbering_starts_at: 0
|
|
|
|
alphanumeric:
|
|
default: *nadstropje
|
|
numeric_probability: 0.69 # With this probability, pick an integer
|
|
roman_numeral_probability: 0.3 # Pick a Roman numeral for the actual value
|
|
alpha_probability: 0.0098 # With this probability, pick a letter e.g. A
|
|
numeric_plus_alpha_probability: 0.0001 # e.g. 2A
|
|
alpha_plus_numeric_probability: 0.0001 # e.g. A2
|
|
|
|
|
|
categories:
|
|
near:
|
|
default:
|
|
canonical: v bližini
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.6
|
|
alternatives:
|
|
- alternative:
|
|
canonical: pri
|
|
probability: 0.4
|
|
|
|
nearby:
|
|
default:
|
|
canonical: v bližini
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.5
|
|
alternatives:
|
|
- alternative:
|
|
canonical: v bližini tukaj
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.3
|
|
- alternative:
|
|
canonical: okoli tukaj
|
|
probability: 0.1
|
|
- alternative:
|
|
canonical: tukaj
|
|
probability: 0.1
|
|
|
|
near_me:
|
|
default:
|
|
canonical: blizu mene
|
|
|
|
# Don't worry about agreement
|
|
in:
|
|
default:
|
|
canonical: v
|
|
|
|
# Probabilities of each phrase
|
|
near_probability: 0.35
|
|
nearby_probability: 0.2
|
|
near_me_probability: 0.1
|
|
in_probability: 0.35
|
|
|
|
directions:
|
|
right: &prav
|
|
canonical: prav
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: right
|
|
left: &levo
|
|
canonical: levo
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: right
|
|
alternatives:
|
|
- alternative: *prav
|
|
probability: 0.5
|
|
- alternative: *levo
|
|
probability: 0.5
|
|
|
|
cardinal_directions:
|
|
east: &vzhod
|
|
canonical: vzhod
|
|
abbreviated: v
|
|
canonical_probability: 0.95
|
|
abbreviated_probability: 0.05
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: v
|
|
direction: right
|
|
numeric_probability: 0.5
|
|
numeric_affix_probability: 0.5
|
|
|
|
west: &zahod
|
|
canonical: zahod
|
|
abbreviated: z
|
|
canonical_probability: 0.95
|
|
abbreviated_probability: 0.05
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: z
|
|
direction: right
|
|
numeric_probability: 0.5
|
|
numeric_affix_probability: 0.5
|
|
|
|
north: &sever
|
|
canonical: sever
|
|
abbreviated: s
|
|
canonical_probability: 0.95
|
|
abbreviated_probability: 0.05
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: s
|
|
direction: right
|
|
numeric_probability: 0.5
|
|
numeric_affix_probability: 0.5
|
|
|
|
south: &jug
|
|
canonical: jug
|
|
abbreviated: j
|
|
sample: true
|
|
canonical_probability: 0.75
|
|
abbreviated_probability: 0.1
|
|
sample_probability: 0.15
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: j
|
|
direction: right
|
|
numeric_probability: 0.5
|
|
numeric_affix_probability: 0.5
|
|
|
|
alternatives:
|
|
- alternative: *sever
|
|
probability: 0.25
|
|
- alternative: *vzhod
|
|
probability: 0.23
|
|
- alternative: *jug
|
|
probability: 0.23
|
|
- alternative: *zahod
|
|
probability: 0.23
|
|
|
|
entrances:
|
|
vhod: &vhod
|
|
canonical: vhod
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
|
|
# Vhod 1, Vhod A, etc.
|
|
alphanumeric: &entrance_alphanumeric
|
|
default: *vhod
|
|
numeric_probability: 0.1 # e.g. Vhod 1
|
|
alpha_probability: 0.85 # e.g. Vhod A
|
|
numeric_plus_alpha_probability: 0.025 # e.g. 1A
|
|
alpha_plus_numeric_probability: 0.025 # e.g. A1
|
|
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|
|
|
|
|
|
staircases:
|
|
stopnisce: &stopnisce
|
|
canonical: stopnišče
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
|
|
|
|
alphanumeric: &staircase_alphanumeric
|
|
default: *stopnisce
|
|
numeric_probability: 0.75
|
|
alpha_probability: 0.2
|
|
numeric_plus_alpha_probability: 0.025
|
|
alpha_plus_numeric_probability: 0.025
|
|
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|
|
|
|
directional:
|
|
direction: right
|
|
direction_probability: 0.85
|
|
modifier:
|
|
alternatives:
|
|
- alternative: *prav
|
|
probability: 0.2
|
|
- alternative: *levo
|
|
probability: 0.2
|
|
- alternative: *sever
|
|
probability: 0.15
|
|
- alternative: *jug
|
|
probability: 0.15
|
|
- alternative: *vzhod
|
|
probability: 0.15
|
|
- alternative: *zahod
|
|
probability: 0.15
|
|
|
|
po_boxes:
|
|
postni_predal: &postni_predal
|
|
canonical: poštni predal
|
|
abbreviated: p.p
|
|
sample: true
|
|
canonical_probability: 0.2
|
|
abbreviated_probability: 0.4
|
|
sample_probability: 0.4
|
|
numeric:
|
|
direction: left
|
|
add_number_phrase: true
|
|
add_number_phrase_probability: 0.2
|
|
|
|
alphanumeric:
|
|
default: *postni_predal
|
|
numeric_probability: 0.9 # pp 123
|
|
alpha_probability: 0.05 # p.p A
|
|
numeric_plus_alpha_probability: 0.04 # pp 123G
|
|
alpha_plus_numeric_probability: 0.01 # pp A123
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|
|
|
|
digits:
|
|
- length: 1
|
|
probability: 0.05
|
|
- length: 2
|
|
probability: 0.1
|
|
- length: 3
|
|
probability: 0.2
|
|
- length: 4
|
|
probability: 0.5
|
|
- length: 5
|
|
probability: 0.1
|
|
- length: 6
|
|
probability: 0.05
|
|
|
|
units:
|
|
stanovanje: &stanovanje
|
|
canonical: stanovanje
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
add_number_phrase: true
|
|
add_number_phrase_probability: 0.1
|
|
|
|
soba: &soba
|
|
canonical: soba
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
add_number_phrase: true
|
|
add_number_phrase_probability: 0.1
|
|
urad: &urad
|
|
canonical: urad
|
|
sample: true
|
|
canonical_probability: 0.6
|
|
sample_probability: 0.4
|
|
numeric:
|
|
direction: left
|
|
add_number_phrase: true
|
|
add_number_phrase_probability: 0.1
|
|
|
|
alphanumeric: &unit_alphanumeric
|
|
default: *stanovanje
|
|
probability: 0.9
|
|
alternatives:
|
|
- alternative: *soba
|
|
probability: 0.1
|
|
numeric_probability: 0.9 # e.g. stanovanje 1
|
|
numeric_plus_alpha_probability: 0.03 # e.g. 1A
|
|
alpha_plus_numeric_probability: 0.03 # e.g. A1
|
|
alpha_probability: 0.04 # e.g. stanovanje A
|
|
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|
|
|
|
# If there are 10 floors, create unit numbers like #301 or #1032
|
|
use_floor_probability: 0.05
|
|
|
|
zones:
|
|
commercial: &commercial_unit_types
|
|
default: *soba
|
|
probability: 0.6
|
|
alternatives:
|
|
- alternative: *urad
|
|
probability: 0.4
|
|
numeric_probability: 0.95 # e.g. soba 1
|
|
numeric_plus_alpha_probability: 0.01 # e.g. soba 1A
|
|
alpha_plus_numeric_probability: 0.01 # e.g. soba A1
|
|
alpha_probability: 0.03 # e.g. soba A
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|
|
university:
|
|
default: *soba
|
|
numeric_probability: 0.95 # e.g. soba 1
|
|
numeric_plus_alpha_probability: 0.01 # e.g. soba 1A
|
|
alpha_plus_numeric_probability: 0.01 # e.g. soba A1
|
|
alpha_probability: 0.03 # e.g. soba A
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|