rsemantic 0.1.4 → 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/README.md +6 -3
- data/TODO.txt +5 -2
- data/lib/semantic/parser.rb +5 -3
- data/lib/semantic/transform/tf_idf_transform.rb +2 -5
- data/lib/semantic/vector_space/builder.rb +1 -1
- data/lib/semantic/vector_space/model.rb +9 -3
- data/lib/semantic/version.rb +2 -2
- data/lib/tasks/rspec.rake +5 -1
- data/resources/ar.stop +162 -0
- data/resources/ca.stop +124 -0
- data/resources/cs.stop +136 -0
- data/resources/da.stop +99 -0
- data/resources/de.stop +996 -0
- data/resources/el.stop +77 -0
- data/resources/{english.stop → en.stop} +0 -0
- data/resources/es.stop +176 -0
- data/resources/fi.stop +747 -0
- data/resources/fr.stop +124 -0
- data/resources/hu.stop +33 -0
- data/resources/id.stop +329 -0
- data/resources/it.stop +132 -0
- data/resources/ja.stop +44 -0
- data/resources/nl.stop +46 -0
- data/resources/no.stop +117 -0
- data/resources/pl.stop +138 -0
- data/resources/pt.stop +145 -0
- data/resources/ru.stop +421 -0
- data/resources/sv.stop +386 -0
- data/resources/tr.stop +112 -0
- metadata +24 -4
data/resources/it.stop
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
1
|
+
a
|
|
2
|
+
adesso
|
|
3
|
+
ai
|
|
4
|
+
al
|
|
5
|
+
alla
|
|
6
|
+
allo
|
|
7
|
+
allora
|
|
8
|
+
altre
|
|
9
|
+
altri
|
|
10
|
+
altro
|
|
11
|
+
anche
|
|
12
|
+
ancora
|
|
13
|
+
avere
|
|
14
|
+
aveva
|
|
15
|
+
avevano
|
|
16
|
+
ben
|
|
17
|
+
buono
|
|
18
|
+
che
|
|
19
|
+
chi
|
|
20
|
+
cinque
|
|
21
|
+
comprare
|
|
22
|
+
con
|
|
23
|
+
consecutivi
|
|
24
|
+
consecutivo
|
|
25
|
+
cosa
|
|
26
|
+
cui
|
|
27
|
+
da
|
|
28
|
+
del
|
|
29
|
+
della
|
|
30
|
+
dello
|
|
31
|
+
dentro
|
|
32
|
+
deve
|
|
33
|
+
devo
|
|
34
|
+
di
|
|
35
|
+
doppio
|
|
36
|
+
due
|
|
37
|
+
e
|
|
38
|
+
ecco
|
|
39
|
+
fare
|
|
40
|
+
fine
|
|
41
|
+
fino
|
|
42
|
+
fra
|
|
43
|
+
gente
|
|
44
|
+
giu
|
|
45
|
+
ha
|
|
46
|
+
hai
|
|
47
|
+
hanno
|
|
48
|
+
ho
|
|
49
|
+
il
|
|
50
|
+
indietro invece
|
|
51
|
+
io
|
|
52
|
+
la
|
|
53
|
+
lavoro
|
|
54
|
+
le
|
|
55
|
+
lei
|
|
56
|
+
lo
|
|
57
|
+
loro
|
|
58
|
+
lui
|
|
59
|
+
lungo
|
|
60
|
+
ma
|
|
61
|
+
me
|
|
62
|
+
meglio
|
|
63
|
+
molta
|
|
64
|
+
molti
|
|
65
|
+
molto
|
|
66
|
+
nei
|
|
67
|
+
nella
|
|
68
|
+
no
|
|
69
|
+
noi
|
|
70
|
+
nome
|
|
71
|
+
nostro
|
|
72
|
+
nove
|
|
73
|
+
nuovi
|
|
74
|
+
nuovo
|
|
75
|
+
o
|
|
76
|
+
oltre
|
|
77
|
+
ora
|
|
78
|
+
otto
|
|
79
|
+
peggio
|
|
80
|
+
pero
|
|
81
|
+
persone
|
|
82
|
+
piu
|
|
83
|
+
poco
|
|
84
|
+
primo
|
|
85
|
+
promesso
|
|
86
|
+
qua
|
|
87
|
+
quarto
|
|
88
|
+
quasi
|
|
89
|
+
quattro
|
|
90
|
+
quello
|
|
91
|
+
questo
|
|
92
|
+
qui
|
|
93
|
+
quindi
|
|
94
|
+
quinto
|
|
95
|
+
rispetto
|
|
96
|
+
sara
|
|
97
|
+
secondo
|
|
98
|
+
sei
|
|
99
|
+
sembra sembrava
|
|
100
|
+
senza
|
|
101
|
+
sette
|
|
102
|
+
sia
|
|
103
|
+
siamo
|
|
104
|
+
siete
|
|
105
|
+
solo
|
|
106
|
+
sono
|
|
107
|
+
sopra
|
|
108
|
+
soprattutto
|
|
109
|
+
sotto
|
|
110
|
+
stati
|
|
111
|
+
stato
|
|
112
|
+
stesso
|
|
113
|
+
su
|
|
114
|
+
subito
|
|
115
|
+
sul
|
|
116
|
+
sulla
|
|
117
|
+
tanto
|
|
118
|
+
te
|
|
119
|
+
tempo
|
|
120
|
+
terzo
|
|
121
|
+
tra
|
|
122
|
+
tre
|
|
123
|
+
triplo
|
|
124
|
+
ultimo
|
|
125
|
+
un
|
|
126
|
+
una
|
|
127
|
+
uno
|
|
128
|
+
va
|
|
129
|
+
vai
|
|
130
|
+
voi
|
|
131
|
+
volte
|
|
132
|
+
vostro
|
data/resources/ja.stop
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
1
|
+
これ
|
|
2
|
+
それ
|
|
3
|
+
あれ
|
|
4
|
+
この
|
|
5
|
+
その
|
|
6
|
+
あの
|
|
7
|
+
ここ
|
|
8
|
+
そこ
|
|
9
|
+
あそこ
|
|
10
|
+
こちら
|
|
11
|
+
どこ
|
|
12
|
+
だれ
|
|
13
|
+
なに
|
|
14
|
+
なん
|
|
15
|
+
何
|
|
16
|
+
私
|
|
17
|
+
貴方
|
|
18
|
+
貴方方
|
|
19
|
+
我々
|
|
20
|
+
私達
|
|
21
|
+
あの人
|
|
22
|
+
あのかた
|
|
23
|
+
彼女
|
|
24
|
+
彼
|
|
25
|
+
です
|
|
26
|
+
あります
|
|
27
|
+
おります
|
|
28
|
+
います
|
|
29
|
+
は
|
|
30
|
+
が
|
|
31
|
+
の
|
|
32
|
+
に
|
|
33
|
+
を
|
|
34
|
+
で
|
|
35
|
+
え
|
|
36
|
+
から
|
|
37
|
+
まで
|
|
38
|
+
より
|
|
39
|
+
も
|
|
40
|
+
どの
|
|
41
|
+
と
|
|
42
|
+
し
|
|
43
|
+
それで
|
|
44
|
+
しかし
|
data/resources/nl.stop
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
aan
|
|
2
|
+
af
|
|
3
|
+
al
|
|
4
|
+
als
|
|
5
|
+
bij
|
|
6
|
+
dan
|
|
7
|
+
dat
|
|
8
|
+
die
|
|
9
|
+
dit
|
|
10
|
+
een
|
|
11
|
+
en
|
|
12
|
+
er
|
|
13
|
+
had
|
|
14
|
+
heb
|
|
15
|
+
hem
|
|
16
|
+
het
|
|
17
|
+
hij
|
|
18
|
+
hoe
|
|
19
|
+
hun
|
|
20
|
+
ik in
|
|
21
|
+
is
|
|
22
|
+
je
|
|
23
|
+
kan
|
|
24
|
+
me
|
|
25
|
+
men
|
|
26
|
+
met
|
|
27
|
+
mij
|
|
28
|
+
nog
|
|
29
|
+
nu
|
|
30
|
+
of
|
|
31
|
+
ons
|
|
32
|
+
ook
|
|
33
|
+
te
|
|
34
|
+
tot
|
|
35
|
+
uit
|
|
36
|
+
van
|
|
37
|
+
was wat
|
|
38
|
+
we
|
|
39
|
+
wel
|
|
40
|
+
wij
|
|
41
|
+
zal
|
|
42
|
+
ze
|
|
43
|
+
zei
|
|
44
|
+
zij
|
|
45
|
+
zo
|
|
46
|
+
zou
|
data/resources/no.stop
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
1
|
+
alle
|
|
2
|
+
andre
|
|
3
|
+
arbeid
|
|
4
|
+
av
|
|
5
|
+
begge
|
|
6
|
+
bort
|
|
7
|
+
bra
|
|
8
|
+
bruke
|
|
9
|
+
da
|
|
10
|
+
denne
|
|
11
|
+
der
|
|
12
|
+
deres
|
|
13
|
+
det
|
|
14
|
+
din
|
|
15
|
+
disse
|
|
16
|
+
du
|
|
17
|
+
eller
|
|
18
|
+
en
|
|
19
|
+
ene
|
|
20
|
+
eneste
|
|
21
|
+
enhver
|
|
22
|
+
enn
|
|
23
|
+
er
|
|
24
|
+
et
|
|
25
|
+
folk
|
|
26
|
+
for
|
|
27
|
+
fordi
|
|
28
|
+
forsÛke
|
|
29
|
+
fra
|
|
30
|
+
fÅ
|
|
31
|
+
fÛr
|
|
32
|
+
fÛrst
|
|
33
|
+
gjorde
|
|
34
|
+
gjÛre
|
|
35
|
+
god
|
|
36
|
+
gÅ
|
|
37
|
+
ha
|
|
38
|
+
hadde
|
|
39
|
+
han
|
|
40
|
+
hans
|
|
41
|
+
hennes
|
|
42
|
+
her
|
|
43
|
+
hva
|
|
44
|
+
hvem
|
|
45
|
+
hver
|
|
46
|
+
hvilken
|
|
47
|
+
hvis
|
|
48
|
+
hvor
|
|
49
|
+
hvordan
|
|
50
|
+
hvorfor i
|
|
51
|
+
ikke
|
|
52
|
+
inn
|
|
53
|
+
innen
|
|
54
|
+
kan
|
|
55
|
+
kunne
|
|
56
|
+
lage
|
|
57
|
+
lang
|
|
58
|
+
lik
|
|
59
|
+
like
|
|
60
|
+
makt
|
|
61
|
+
mange
|
|
62
|
+
med
|
|
63
|
+
meg
|
|
64
|
+
meget
|
|
65
|
+
men
|
|
66
|
+
mens
|
|
67
|
+
mer
|
|
68
|
+
mest
|
|
69
|
+
min
|
|
70
|
+
mye
|
|
71
|
+
mÅ
|
|
72
|
+
mÅte
|
|
73
|
+
navn
|
|
74
|
+
nei
|
|
75
|
+
ny
|
|
76
|
+
nÅ
|
|
77
|
+
nÅr
|
|
78
|
+
og
|
|
79
|
+
ogsÅ
|
|
80
|
+
om
|
|
81
|
+
opp
|
|
82
|
+
oss
|
|
83
|
+
over
|
|
84
|
+
part
|
|
85
|
+
punkt
|
|
86
|
+
pÅ
|
|
87
|
+
rett
|
|
88
|
+
riktig
|
|
89
|
+
samme
|
|
90
|
+
sant
|
|
91
|
+
si
|
|
92
|
+
siden
|
|
93
|
+
sist
|
|
94
|
+
skulle
|
|
95
|
+
slik
|
|
96
|
+
slutt
|
|
97
|
+
som
|
|
98
|
+
start
|
|
99
|
+
stille sÅ
|
|
100
|
+
tid
|
|
101
|
+
til
|
|
102
|
+
tilbake
|
|
103
|
+
tilstand
|
|
104
|
+
under
|
|
105
|
+
ut
|
|
106
|
+
uten
|
|
107
|
+
var
|
|
108
|
+
ved
|
|
109
|
+
verdi
|
|
110
|
+
vi
|
|
111
|
+
vil
|
|
112
|
+
ville
|
|
113
|
+
vite
|
|
114
|
+
vÅr
|
|
115
|
+
vÖre
|
|
116
|
+
vÖrt
|
|
117
|
+
Å
|
data/resources/pl.stop
ADDED
|
@@ -0,0 +1,138 @@
|
|
|
1
|
+
ach
|
|
2
|
+
aj
|
|
3
|
+
albo
|
|
4
|
+
bardzo
|
|
5
|
+
bez
|
|
6
|
+
bo
|
|
7
|
+
być
|
|
8
|
+
ci
|
|
9
|
+
cię
|
|
10
|
+
ciebie
|
|
11
|
+
co
|
|
12
|
+
czy
|
|
13
|
+
daleko
|
|
14
|
+
dla
|
|
15
|
+
dlaczego
|
|
16
|
+
dlatego
|
|
17
|
+
do
|
|
18
|
+
dobrze
|
|
19
|
+
dokąd
|
|
20
|
+
dość
|
|
21
|
+
dużo
|
|
22
|
+
dwa
|
|
23
|
+
dwaj
|
|
24
|
+
dwie
|
|
25
|
+
dwoje
|
|
26
|
+
dziś
|
|
27
|
+
dzisiaj
|
|
28
|
+
gdyby
|
|
29
|
+
gdzie
|
|
30
|
+
go
|
|
31
|
+
ich
|
|
32
|
+
ile
|
|
33
|
+
im
|
|
34
|
+
inny
|
|
35
|
+
ja
|
|
36
|
+
ją
|
|
37
|
+
jak
|
|
38
|
+
jakby
|
|
39
|
+
jaki
|
|
40
|
+
je
|
|
41
|
+
jeden
|
|
42
|
+
jedna
|
|
43
|
+
jedno
|
|
44
|
+
jego
|
|
45
|
+
jej
|
|
46
|
+
jemu
|
|
47
|
+
jeśli
|
|
48
|
+
jest
|
|
49
|
+
jestem
|
|
50
|
+
jeżeli
|
|
51
|
+
już
|
|
52
|
+
każdy
|
|
53
|
+
kiedy
|
|
54
|
+
kierunku
|
|
55
|
+
kto
|
|
56
|
+
ku
|
|
57
|
+
lub
|
|
58
|
+
ma
|
|
59
|
+
mają
|
|
60
|
+
mam
|
|
61
|
+
mi
|
|
62
|
+
mną
|
|
63
|
+
mnie
|
|
64
|
+
moi
|
|
65
|
+
mój
|
|
66
|
+
moja
|
|
67
|
+
moje
|
|
68
|
+
może
|
|
69
|
+
mu
|
|
70
|
+
my
|
|
71
|
+
na
|
|
72
|
+
nam
|
|
73
|
+
nami
|
|
74
|
+
nas
|
|
75
|
+
nasi
|
|
76
|
+
nasz
|
|
77
|
+
nasza
|
|
78
|
+
nasze
|
|
79
|
+
natychmiast
|
|
80
|
+
nią
|
|
81
|
+
nic
|
|
82
|
+
nich
|
|
83
|
+
nie
|
|
84
|
+
niego
|
|
85
|
+
niej
|
|
86
|
+
niemu
|
|
87
|
+
nigdy
|
|
88
|
+
nim
|
|
89
|
+
nimi
|
|
90
|
+
niż
|
|
91
|
+
obok
|
|
92
|
+
od
|
|
93
|
+
około
|
|
94
|
+
on
|
|
95
|
+
ona
|
|
96
|
+
one
|
|
97
|
+
oni
|
|
98
|
+
ono
|
|
99
|
+
owszem
|
|
100
|
+
po
|
|
101
|
+
pod
|
|
102
|
+
ponieważ
|
|
103
|
+
przed
|
|
104
|
+
przedtem
|
|
105
|
+
są
|
|
106
|
+
sam
|
|
107
|
+
sama
|
|
108
|
+
się
|
|
109
|
+
skąd
|
|
110
|
+
tak
|
|
111
|
+
taki
|
|
112
|
+
tam
|
|
113
|
+
ten
|
|
114
|
+
to
|
|
115
|
+
tobą
|
|
116
|
+
tobie
|
|
117
|
+
tu
|
|
118
|
+
tutaj
|
|
119
|
+
twoi
|
|
120
|
+
twój
|
|
121
|
+
twoja
|
|
122
|
+
twoje
|
|
123
|
+
ty
|
|
124
|
+
wam
|
|
125
|
+
wami
|
|
126
|
+
was
|
|
127
|
+
wasi
|
|
128
|
+
wasz
|
|
129
|
+
wasza
|
|
130
|
+
wasze
|
|
131
|
+
we
|
|
132
|
+
więc
|
|
133
|
+
wszystko
|
|
134
|
+
wtedy
|
|
135
|
+
wy
|
|
136
|
+
żaden
|
|
137
|
+
zawsze
|
|
138
|
+
że
|