Spaces:
Build error
Build error
Ling Luo
commited on
Commit
•
d43bc33
1
Parent(s):
3ab07ec
add file
Browse files- vocab/char.vocab +593 -0
- vocab/pos.vocab +50 -0
vocab/char.vocab
ADDED
@@ -0,0 +1,593 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
E
|
2 |
+
x
|
3 |
+
p
|
4 |
+
r
|
5 |
+
e
|
6 |
+
s
|
7 |
+
i
|
8 |
+
o
|
9 |
+
n
|
10 |
+
f
|
11 |
+
v
|
12 |
+
a
|
13 |
+
c
|
14 |
+
u
|
15 |
+
l
|
16 |
+
d
|
17 |
+
t
|
18 |
+
h
|
19 |
+
g
|
20 |
+
w
|
21 |
+
m
|
22 |
+
q
|
23 |
+
:
|
24 |
+
5
|
25 |
+
3
|
26 |
+
.
|
27 |
+
A
|
28 |
+
I
|
29 |
+
M
|
30 |
+
S
|
31 |
+
T
|
32 |
+
(
|
33 |
+
V
|
34 |
+
G
|
35 |
+
F
|
36 |
+
)
|
37 |
+
;
|
38 |
+
H
|
39 |
+
O
|
40 |
+
D
|
41 |
+
4
|
42 |
+
,
|
43 |
+
%
|
44 |
+
y
|
45 |
+
N
|
46 |
+
b
|
47 |
+
C
|
48 |
+
L
|
49 |
+
U
|
50 |
+
R
|
51 |
+
B
|
52 |
+
J
|
53 |
+
'
|
54 |
+
K
|
55 |
+
—
|
56 |
+
6
|
57 |
+
X
|
58 |
+
P
|
59 |
+
1
|
60 |
+
+
|
61 |
+
j
|
62 |
+
-
|
63 |
+
z
|
64 |
+
W
|
65 |
+
k
|
66 |
+
Q
|
67 |
+
9
|
68 |
+
‘
|
69 |
+
’
|
70 |
+
8
|
71 |
+
<
|
72 |
+
0
|
73 |
+
χ
|
74 |
+
Z
|
75 |
+
©
|
76 |
+
2
|
77 |
+
[
|
78 |
+
]
|
79 |
+
–
|
80 |
+
7
|
81 |
+
/
|
82 |
+
=
|
83 |
+
α
|
84 |
+
β
|
85 |
+
é
|
86 |
+
′
|
87 |
+
Y
|
88 |
+
μ
|
89 |
+
×
|
90 |
+
°
|
91 |
+
∼
|
92 |
+
>
|
93 |
+
Ψ
|
94 |
+
ö
|
95 |
+
−
|
96 |
+
≈
|
97 |
+
?
|
98 |
+
"
|
99 |
+
κ
|
100 |
+
µ
|
101 |
+
“
|
102 |
+
”
|
103 |
+
Δ
|
104 |
+
γ
|
105 |
+
‐
|
106 |
+
≤
|
107 |
+
𝒜
|
108 |
+
#
|
109 |
+
*
|
110 |
+
~
|
111 |
+
⩾
|
112 |
+
±
|
113 |
+
≥
|
114 |
+
→
|
115 |
+
†
|
116 |
+
δ
|
117 |
+
τ
|
118 |
+
⩽
|
119 |
+
è
|
120 |
+
ε
|
121 |
+
λ
|
122 |
+
ü
|
123 |
+
ι
|
124 |
+
•
|
125 |
+
ς
|
126 |
+
π
|
127 |
+
™
|
128 |
+
`
|
129 |
+
φ
|
130 |
+
θ
|
131 |
+
Τ
|
132 |
+
·
|
133 |
+
ß
|
134 |
+
&
|
135 |
+
ɛ
|
136 |
+
ω
|
137 |
+
̈
|
138 |
+
_
|
139 |
+
!
|
140 |
+
\
|
141 |
+
{
|
142 |
+
}
|
143 |
+
Χ
|
144 |
+
$
|
145 |
+
®
|
146 |
+
↓
|
147 |
+
‡
|
148 |
+
σ
|
149 |
+
Φ
|
150 |
+
ñ
|
151 |
+
ó
|
152 |
+
º
|
153 |
+
ρ
|
154 |
+
ä
|
155 |
+
ψ
|
156 |
+
…
|
157 |
+
í
|
158 |
+
Å
|
159 |
+
ë
|
160 |
+
ç
|
161 |
+
«
|
162 |
+
Ø
|
163 |
+
Ω
|
164 |
+
η
|
165 |
+
Ö
|
166 |
+
ù
|
167 |
+
á
|
168 |
+
✓
|
169 |
+
£
|
170 |
+
●
|
171 |
+
○
|
172 |
+
ï
|
173 |
+
℃
|
174 |
+
ζ
|
175 |
+
@
|
176 |
+
⃞
|
177 |
+
≪
|
178 |
+
▪
|
179 |
+
§
|
180 |
+
ξ
|
181 |
+
|
|
182 |
+
▴
|
183 |
+
♦
|
184 |
+
▾
|
185 |
+
ò
|
186 |
+
∞
|
187 |
+
↠
|
188 |
+
ν
|
189 |
+
ã
|
190 |
+
≍
|
191 |
+
ø
|
192 |
+
˜
|
193 |
+
^
|
194 |
+
ê
|
195 |
+
ú
|
196 |
+
↔
|
197 |
+
û
|
198 |
+
´
|
199 |
+
∣
|
200 |
+
≫
|
201 |
+
ℓ
|
202 |
+
ý
|
203 |
+
∊
|
204 |
+
.
|
205 |
+
,
|
206 |
+
▿
|
207 |
+
∆
|
208 |
+
ℬ
|
209 |
+
ô
|
210 |
+
≅
|
211 |
+
č
|
212 |
+
¼
|
213 |
+
à
|
214 |
+
ϵ
|
215 |
+
■
|
216 |
+
∑
|
217 |
+
Æ
|
218 |
+
æ
|
219 |
+
〈
|
220 |
+
〉
|
221 |
+
⋄
|
222 |
+
€
|
223 |
+
↑
|
224 |
+
″
|
225 |
+
â
|
226 |
+
÷
|
227 |
+
√
|
228 |
+
Γ
|
229 |
+
Å
|
230 |
+
ŕ
|
231 |
+
Σ
|
232 |
+
∫
|
233 |
+
š
|
234 |
+
◦
|
235 |
+
Β
|
236 |
+
▵
|
237 |
+
¤
|
238 |
+
▲
|
239 |
+
∷
|
240 |
+
∈
|
241 |
+
»
|
242 |
+
∶
|
243 |
+
Θ
|
244 |
+
Á
|
245 |
+
△
|
246 |
+
ϕ
|
247 |
+
ˆ
|
248 |
+
∇
|
249 |
+
¥
|
250 |
+
□
|
251 |
+
ŧ
|
252 |
+
▼
|
253 |
+
∩
|
254 |
+
⊥
|
255 |
+
¶
|
256 |
+
Α
|
257 |
+
ć
|
258 |
+
Π
|
259 |
+
∗
|
260 |
+
▶
|
261 |
+
|
262 |
+
☆
|
263 |
+
Ä
|
264 |
+
ì
|
265 |
+
Ƶ
|
266 |
+
◆
|
267 |
+
⅓
|
268 |
+
ℳ
|
269 |
+
∀
|
270 |
+
𝒞
|
271 |
+
̃
|
272 |
+
※
|
273 |
+
‰
|
274 |
+
♀
|
275 |
+
♂
|
276 |
+
‖
|
277 |
+
∏
|
278 |
+
≠
|
279 |
+
ϑ
|
280 |
+
Ü
|
281 |
+
|
282 |
+
✞
|
283 |
+
⇆
|
284 |
+
½
|
285 |
+
ϊ
|
286 |
+
Ḅ
|
287 |
+
⇑
|
288 |
+
⇓
|
289 |
+
ạ
|
290 |
+
²
|
291 |
+
◇
|
292 |
+
ɸ
|
293 |
+
å
|
294 |
+
ş
|
295 |
+
∕
|
296 |
+
≡
|
297 |
+
¾
|
298 |
+
Η
|
299 |
+
∅
|
300 |
+
♣
|
301 |
+
✩
|
302 |
+
←
|
303 |
+
◂
|
304 |
+
É
|
305 |
+
Ф
|
306 |
+
„
|
307 |
+
¬
|
308 |
+
♯
|
309 |
+
≦
|
310 |
+
≧
|
311 |
+
ł
|
312 |
+
Ł
|
313 |
+
ź
|
314 |
+
ń
|
315 |
+
Ⅲ
|
316 |
+
∝
|
317 |
+
Ñ
|
318 |
+
⇒
|
319 |
+
∧
|
320 |
+
Ι
|
321 |
+
♠
|
322 |
+
Μ
|
323 |
+
►
|
324 |
+
̀
|
325 |
+
|
326 |
+
ǹ
|
327 |
+
fi
|
328 |
+
ı
|
329 |
+
Ĝ
|
330 |
+
ĝ
|
331 |
+
̂
|
332 |
+
¯
|
333 |
+
fl
|
334 |
+
œ
|
335 |
+
ś
|
336 |
+
―
|
337 |
+
∎
|
338 |
+
˚
|
339 |
+
Ρ
|
340 |
+
⋅
|
341 |
+
‟
|
342 |
+
ą
|
343 |
+
‑
|
344 |
+
Ν
|
345 |
+
║
|
346 |
+
Λ
|
347 |
+
₁
|
348 |
+
₂
|
349 |
+
ℒ
|
350 |
+
、
|
351 |
+
ª
|
352 |
+
ĸ
|
353 |
+
▸
|
354 |
+
‴
|
355 |
+
◊
|
356 |
+
ů
|
357 |
+
①
|
358 |
+
②
|
359 |
+
ο
|
360 |
+
έ
|
361 |
+
‒
|
362 |
+
Č
|
363 |
+
ό
|
364 |
+
⋆
|
365 |
+
⌊
|
366 |
+
⌋
|
367 |
+
⋯
|
368 |
+
;
|
369 |
+
⊕
|
370 |
+
|
371 |
+
⁄
|
372 |
+
Ɣ
|
373 |
+
đ
|
374 |
+
Ⅳ
|
375 |
+
Ó
|
376 |
+
Ⅰ
|
377 |
+
Ⅱ
|
378 |
+
ー
|
379 |
+
∙
|
380 |
+
þ
|
381 |
+
↖
|
382 |
+
׳
|
383 |
+
Ε
|
384 |
+
➔
|
385 |
+
⊂
|
386 |
+
⋍
|
387 |
+
¢
|
388 |
+
Л
|
389 |
+
★
|
390 |
+
☒
|
391 |
+
█
|
392 |
+
⇐
|
393 |
+
ϒ
|
394 |
+
∂
|
395 |
+
ї
|
396 |
+
⁎
|
397 |
+
ɣ
|
398 |
+
№
|
399 |
+
ř
|
400 |
+
˙
|
401 |
+
є
|
402 |
+
ę
|
403 |
+
⊿
|
404 |
+
✔
|
405 |
+
✖
|
406 |
+
Р
|
407 |
+
∽
|
408 |
+
ʼ
|
409 |
+
‚
|
410 |
+
Ç
|
411 |
+
Ω
|
412 |
+
⃗
|
413 |
+
⟨
|
414 |
+
⟩
|
415 |
+
ʋ
|
416 |
+
Ʃ
|
417 |
+
𝒟
|
418 |
+
ℛ
|
419 |
+
𝒮
|
420 |
+
⊗
|
421 |
+
𝒫
|
422 |
+
¦
|
423 |
+
́
|
424 |
+
̄
|
425 |
+
î
|
426 |
+
с
|
427 |
+
。
|
428 |
+
¸
|
429 |
+
Κ
|
430 |
+
Ο
|
431 |
+
☑
|
432 |
+
˗
|
433 |
+
─
|
434 |
+
│
|
435 |
+
⌈
|
436 |
+
⌉
|
437 |
+
Ī
|
438 |
+
◼
|
439 |
+
◻
|
440 |
+
◯
|
441 |
+
≃
|
442 |
+
③
|
443 |
+
④
|
444 |
+
⑤
|
445 |
+
⑥
|
446 |
+
⑦
|
447 |
+
К
|
448 |
+
˃
|
449 |
+
‾
|
450 |
+
|
451 |
+
ż
|
452 |
+
С
|
453 |
+
∪
|
454 |
+
Ú
|
455 |
+
|
456 |
+
¨
|
457 |
+
━
|
458 |
+
✚
|
459 |
+
+
|
460 |
+
ʹ
|
461 |
+
ℝ
|
462 |
+
Š
|
463 |
+
➢
|
464 |
+
ǒ
|
465 |
+
ā
|
466 |
+
ǎ
|
467 |
+
ǐ
|
468 |
+
ğ
|
469 |
+
ɩ
|
470 |
+
Υ
|
471 |
+
ʹ
|
472 |
+
Ⅴ
|
473 |
+
‛
|
474 |
+
ɑ
|
475 |
+
Ê
|
476 |
+
ǂ
|
477 |
+
|
478 |
+
˖
|
479 |
+
⇔
|
480 |
+
|
481 |
+
⑰
|
482 |
+
⑭
|
483 |
+
⑪
|
484 |
+
Œ
|
485 |
+
ffl
|
486 |
+
ℏ
|
487 |
+
∘
|
488 |
+
Ǻ
|
489 |
+
΄
|
490 |
+
ᵠ
|
491 |
+
|
492 |
+
›
|
493 |
+
Ⓡ
|
494 |
+
ƒ
|
495 |
+
≙
|
496 |
+
ү
|
497 |
+
∖
|
498 |
+
ℕ
|
499 |
+
ň
|
500 |
+
≔
|
501 |
+
ų
|
502 |
+
↗
|
503 |
+
↘
|
504 |
+
↙
|
505 |
+
ۛ
|
506 |
+
Ş
|
507 |
+
İ
|
508 |
+
ộ
|
509 |
+
ả
|
510 |
+
ằ
|
511 |
+
Đ
|
512 |
+
ị
|
513 |
+
ắ
|
514 |
+
ơ
|
515 |
+
ệ
|
516 |
+
ư
|
517 |
+
ọ
|
518 |
+
З
|
519 |
+
ˊ
|
520 |
+
◎
|
521 |
+
ff
|
522 |
+
⇀
|
523 |
+
к
|
524 |
+
☐
|
525 |
+

|
526 |
+
Ȼ
|
527 |
+
Ȣ
|
528 |
+
ĥ
|
529 |
+
Ô
|
530 |
+
𝜸
|
531 |
+
ō
|
532 |
+
Ā
|
533 |
+
ī
|
534 |
+
Ō
|
535 |
+
ū
|
536 |
+
≲
|
537 |
+
⟶
|
538 |
+
<
|
539 |
+
Õ
|
540 |
+
⎼
|
541 |
+
¹
|
542 |
+
Ɛ
|
543 |
+
↦
|
544 |
+
х
|
545 |
+
õ
|
546 |
+
˂
|
547 |
+
▮
|
548 |
+
Ï
|
549 |
+
⋮
|
550 |
+
⇌
|
551 |
+
ᅟ
|
552 |
+
❖
|
553 |
+
�
|
554 |
+
‧
|
555 |
+
𝜀
|
556 |
+
|
557 |
+
∥
|
558 |
+
(
|
559 |
+
)
|
560 |
+
︸
|
561 |
+
·
|
562 |
+
ᴋ
|
563 |
+
³
|
564 |
+
⁑
|
565 |
+
𝛾
|
566 |
+
⎧
|
567 |
+
Ž
|
568 |
+
┼
|
569 |
+
➞
|
570 |
+
~
|
571 |
+
ɤ
|
572 |
+
ҫ
|
573 |
+
Ɵ
|
574 |
+
ž
|
575 |
+
ά
|
576 |
+
⌐
|
577 |
+
ƙ
|
578 |
+
ƴ
|
579 |
+
⁰
|
580 |
+
Ƙ
|
581 |
+
М
|
582 |
+
А
|
583 |
+
ă
|
584 |
+
Ⅵ
|
585 |
+
ᵃ
|
586 |
+
ᵇ
|
587 |
+
⁞
|
588 |
+
ˉ
|
589 |
+
>
|
590 |
+
≳
|
591 |
+
⊆
|
592 |
+
ℋ
|
593 |
+
Ã
|
vocab/pos.vocab
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
NN
|
2 |
+
IN
|
3 |
+
SYM
|
4 |
+
VBZ
|
5 |
+
DT
|
6 |
+
JJ
|
7 |
+
,
|
8 |
+
VBN
|
9 |
+
NNS
|
10 |
+
(
|
11 |
+
RB
|
12 |
+
)
|
13 |
+
CC
|
14 |
+
.
|
15 |
+
VBP
|
16 |
+
TO
|
17 |
+
NNP
|
18 |
+
:
|
19 |
+
CD
|
20 |
+
VBD
|
21 |
+
PRP
|
22 |
+
VB
|
23 |
+
PRP$
|
24 |
+
WDT
|
25 |
+
VBG
|
26 |
+
RBS
|
27 |
+
MD
|
28 |
+
FW
|
29 |
+
WP
|
30 |
+
JJS
|
31 |
+
AFX
|
32 |
+
JJR
|
33 |
+
POS
|
34 |
+
``
|
35 |
+
''
|
36 |
+
RBR
|
37 |
+
EX
|
38 |
+
WRB
|
39 |
+
RP
|
40 |
+
$
|
41 |
+
HYPH
|
42 |
+
WP$
|
43 |
+
LS
|
44 |
+
#
|
45 |
+
PDT
|
46 |
+
NNPS
|
47 |
+
NN|CD
|
48 |
+
NF-
|
49 |
+
UH
|
50 |
+
G
|