add tokenizers and dict files
Browse files
dicts/dict.transformer.base.en.const.txt
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
</NP> 834587
|
| 2 |
+
<NP> 834587
|
| 3 |
+
NN 655960
|
| 4 |
+
IN 559326
|
| 5 |
+
DT 458456
|
| 6 |
+
</VP> 450160
|
| 7 |
+
<VP> 450160
|
| 8 |
+
NNP 405496
|
| 9 |
+
</S> 300422
|
| 10 |
+
<S> 300422
|
| 11 |
+
JJ 292882
|
| 12 |
+
NNS 272432
|
| 13 |
+
. 251036
|
| 14 |
+
XX 250846
|
| 15 |
+
</PP> 243084
|
| 16 |
+
<PP> 243084
|
| 17 |
+
, 230006
|
| 18 |
+
PRP 225438
|
| 19 |
+
RB 224084
|
| 20 |
+
VB 181970
|
| 21 |
+
VBD 169356
|
| 22 |
+
CC 154986
|
| 23 |
+
</TOP> 141871
|
| 24 |
+
<TOP> 141871
|
| 25 |
+
VBZ 124814
|
| 26 |
+
VBP 107908
|
| 27 |
+
VBN 104034
|
| 28 |
+
CD 101496
|
| 29 |
+
</SBAR> 85487
|
| 30 |
+
<SBAR> 85487
|
| 31 |
+
VBG 85382
|
| 32 |
+
TO 76424
|
| 33 |
+
</ADVP> 73664
|
| 34 |
+
<ADVP> 73664
|
| 35 |
+
MD 63004
|
| 36 |
+
PRP$ 57414
|
| 37 |
+
</ADJP> 45325
|
| 38 |
+
<ADJP> 45325
|
| 39 |
+
HYPH 35952
|
| 40 |
+
</NML> 34655
|
| 41 |
+
<NML> 34655
|
| 42 |
+
UH 34140
|
| 43 |
+
POS 33028
|
| 44 |
+
</WHNP> 25806
|
| 45 |
+
<WHNP> 25806
|
| 46 |
+
WP 25254
|
| 47 |
+
WDT 24226
|
| 48 |
+
'' 23860
|
| 49 |
+
`` 22524
|
| 50 |
+
: 21704
|
| 51 |
+
RP 20390
|
| 52 |
+
WRB 20208
|
| 53 |
+
</INTJ> 16172
|
| 54 |
+
<INTJ> 16172
|
| 55 |
+
" 15072
|
| 56 |
+
JJR 13996
|
| 57 |
+
NNPS 13962
|
| 58 |
+
</QP> 11774
|
| 59 |
+
<QP> 11774
|
| 60 |
+
VERB 10126
|
| 61 |
+
</PRT> 9713
|
| 62 |
+
<PRT> 9713
|
| 63 |
+
</WHADVP> 9662
|
| 64 |
+
<WHADVP> 9662
|
| 65 |
+
$ 9022
|
| 66 |
+
EX 8722
|
| 67 |
+
JJS 7716
|
| 68 |
+
RBR 7040
|
| 69 |
+
) 6862
|
| 70 |
+
</EDITED> 6841
|
| 71 |
+
<EDITED> 6841
|
| 72 |
+
( 6782
|
| 73 |
+
</SQ> 6255
|
| 74 |
+
<SQ> 6255
|
| 75 |
+
</FRAG> 5225
|
| 76 |
+
<FRAG> 5225
|
| 77 |
+
PDT 5088
|
| 78 |
+
</PRN> 3999
|
| 79 |
+
<PRN> 3999
|
| 80 |
+
</SINV> 3317
|
| 81 |
+
<SINV> 3317
|
| 82 |
+
</SBARQ> 3305
|
| 83 |
+
<SBARQ> 3305
|
| 84 |
+
RBS 2882
|
| 85 |
+
FW 1956
|
| 86 |
+
</UCP> 1534
|
| 87 |
+
<UCP> 1534
|
| 88 |
+
NFP 1348
|
| 89 |
+
</CONJP> 1103
|
| 90 |
+
<CONJP> 1103
|
| 91 |
+
SYM 1102
|
| 92 |
+
</WHPP> 1002
|
| 93 |
+
<WHPP> 1002
|
| 94 |
+
</X> 816
|
| 95 |
+
<X> 816
|
| 96 |
+
' 782
|
| 97 |
+
WP$ 750
|
| 98 |
+
</EMBED> 718
|
| 99 |
+
<EMBED> 718
|
| 100 |
+
LS 690
|
| 101 |
+
</WHADJP> 516
|
| 102 |
+
<WHADJP> 516
|
| 103 |
+
ADD 460
|
| 104 |
+
</LST> 356
|
| 105 |
+
<LST> 356
|
| 106 |
+
</META> 288
|
| 107 |
+
<META> 288
|
| 108 |
+
</RRC> 232
|
| 109 |
+
<RRC> 232
|
| 110 |
+
</NAC> 218
|
| 111 |
+
<NAC> 218
|
| 112 |
+
</NX> 74
|
| 113 |
+
<NX> 74
|
| 114 |
+
AFX 62
|
| 115 |
+
</XX> 35
|
| 116 |
+
<XX> 35
|
dicts/dict.transformer.base.en.mt.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
dicts/dict.transformer.large.multi.mtpg.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizers/bpe32k.en/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizers/bpe32k.en/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizers/bpe32k.ko/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizers/bpe32k.ko/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|