KoichiYasuoka commited on
Commit
9058a3d
1 Parent(s): 72935a5

model improved

Browse files
Files changed (4) hide show
  1. config.json +400 -364
  2. pytorch_model.bin +2 -2
  3. supar.model +2 -2
  4. tokenizer.json +14 -0
config.json CHANGED
@@ -24,181 +24,187 @@
24
  "12": "B-ADP|\u683c\u52a9\u8a5e|_",
25
  "13": "B-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
26
  "14": "B-ADV|\u526f\u8a5e|_",
27
- "15": "B-ADV|\u9593\u6295\u8a5e|_",
28
- "16": "B-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
29
- "17": "B-AUX|\u52a9\u52d5\u8a5e|_",
30
- "18": "B-AUX|\u52a9\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
31
- "19": "B-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_",
32
- "20": "B-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
33
- "21": "B-CCONJ|\u63a5\u7d9a\u8a5e|_",
34
- "22": "B-DET|\u526f\u8a5e|_",
35
- "23": "B-DET|\u9023\u4f53\u8a5e|_",
36
- "24": "B-DET|\u9023\u4f53\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
37
- "25": "B-INTJ|\u9593\u6295\u8a5e|_",
38
- "26": "B-NOUN|\u4eba\u79f0\u63a5\u8f9e|_",
39
- "27": "B-NOUN|\u4ee3\u540d\u8a5e|_",
40
- "28": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
41
- "29": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
42
- "30": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_",
43
- "31": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
44
- "32": "B-NOUN|\u540d\u8a5e|_",
45
- "33": "B-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
46
- "34": "B-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_",
47
- "35": "B-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
48
- "36": "B-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_",
49
- "37": "B-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
50
- "38": "B-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
51
- "39": "B-NOUN|\u56fa\u6709\u540d\u8a5e|_",
52
- "40": "B-NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
53
- "41": "B-NUM|\u6570\u8a5e|_",
54
- "42": "B-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_",
55
- "43": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_",
56
- "44": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
57
- "45": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
58
- "46": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
59
- "47": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
60
- "48": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_",
61
- "49": "B-PART|\u52a9\u52d5\u8a5e|_",
62
- "50": "B-PART|\u63a5\u5c3e\u8f9e|_",
63
- "51": "B-PART|\u63a5\u7d9a\u52a9\u8a5e|_",
64
- "52": "B-PART|\u63a5\u982d\u8f9e|_",
65
- "53": "B-PART|\u7d42\u52a9\u8a5e|_",
66
- "54": "B-PART|\u81ea\u52d5\u8a5e|_",
67
- "55": "B-PRON|\u4ee3\u540d\u8a5e|_",
68
- "56": "B-PROPN|\u56fa\u6709\u540d\u8a5e|_",
69
- "57": "B-PUNCT|\u8a18\u53f7|_",
70
- "58": "B-SCONJ|\u4ed6\u52d5\u8a5e|_",
71
- "59": "B-SCONJ|\u526f\u8a5e|_",
72
- "60": "B-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
73
- "61": "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
74
- "62": "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_",
75
- "63": "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+DET|\u9023\u4f53\u8a5e|_",
76
- "64": "B-SCONJ|\u63a5\u7d9a\u8a5e|_",
77
- "65": "B-SCONJ|\u683c\u52a9\u8a5e|_",
78
- "66": "B-SCONJ|\u7d42\u52a9\u8a5e|_",
79
- "67": "B-SYM|_|_",
80
- "68": "B-VERB|\u4ed6\u52d5\u8a5e|_",
81
- "69": "B-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
82
- "70": "B-VERB|\u5b8c\u5168\u52d5\u8a5e|_",
83
- "71": "B-VERB|\u683c\u52a9\u8a5e|_",
84
- "72": "B-VERB|\u81ea\u52d5\u8a5e|_",
85
- "73": "B-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_",
86
- "74": "B-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
87
- "75": "B-VERT|\u4ed6\u52d5\u8a5e|_",
88
- "76": "B-X|_|_",
89
- "77": "CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
90
- "78": "CCONJ|\u63a5\u7d9a\u8a5e|_",
91
- "79": "DET|\u9023\u4f53\u8a5e|_",
92
- "80": "DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_",
93
- "81": "DET|\u9023\u4f53\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_",
94
- "82": "I-ADP|\u526f\u52a9\u8a5e|_",
95
- "83": "I-ADP|\u526f\u8a5e|_",
96
- "84": "I-ADP|\u5f8c\u7f6e\u526f\u8a5e|_",
97
- "85": "I-ADP|\u683c\u52a9\u8a5e|_",
98
- "86": "I-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
99
- "87": "I-ADV|\u526f\u8a5e|_",
100
- "88": "I-ADV|\u9593\u6295\u8a5e|_",
101
- "89": "I-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
102
- "90": "I-AUX|\u52a9\u52d5\u8a5e|_",
103
- "91": "I-AUX|\u52a9\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
104
- "92": "I-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_",
105
- "93": "I-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
106
- "94": "I-CCONJ|\u63a5\u7d9a\u8a5e|_",
107
- "95": "I-DET|\u526f\u8a5e|_",
108
- "96": "I-DET|\u9023\u4f53\u8a5e|_",
109
- "97": "I-DET|\u9023\u4f53\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
110
- "98": "I-INTJ|\u9593\u6295\u8a5e|_",
111
- "99": "I-NOUN|\u4eba\u79f0\u63a5\u8f9e|_",
112
- "100": "I-NOUN|\u4ee3\u540d\u8a5e|_",
113
- "101": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
114
- "102": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
115
- "103": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_",
116
- "104": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
117
- "105": "I-NOUN|\u540d\u8a5e|_",
118
- "106": "I-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
119
- "107": "I-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_",
120
- "108": "I-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
121
- "109": "I-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_",
122
- "110": "I-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
123
- "111": "I-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
124
- "112": "I-NOUN|\u56fa\u6709\u540d\u8a5e|_",
125
- "113": "I-NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
126
- "114": "I-NUM|\u6570\u8a5e|_",
127
- "115": "I-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_",
128
- "116": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_",
129
- "117": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
130
- "118": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
131
- "119": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
132
- "120": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
133
- "121": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_",
134
- "122": "I-PART|\u52a9\u52d5\u8a5e|_",
135
- "123": "I-PART|\u63a5\u5c3e\u8f9e|_",
136
- "124": "I-PART|\u63a5\u7d9a\u52a9\u8a5e|_",
137
- "125": "I-PART|\u63a5\u982d\u8f9e|_",
138
- "126": "I-PART|\u7d42\u52a9\u8a5e|_",
139
- "127": "I-PART|\u81ea\u52d5\u8a5e|_",
140
- "128": "I-PRON|\u4ee3\u540d\u8a5e|_",
141
- "129": "I-PROPN|\u56fa\u6709\u540d\u8a5e|_",
142
- "130": "I-PUNCT|\u8a18\u53f7|_",
143
- "131": "I-SCONJ|\u4ed6\u52d5\u8a5e|_",
144
- "132": "I-SCONJ|\u526f\u8a5e|_",
145
- "133": "I-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
146
- "134": "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
147
- "135": "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_",
148
- "136": "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+DET|\u9023\u4f53\u8a5e|_",
149
- "137": "I-SCONJ|\u63a5\u7d9a\u8a5e|_",
150
- "138": "I-SCONJ|\u683c\u52a9\u8a5e|_",
151
- "139": "I-SCONJ|\u7d42\u52a9\u8a5e|_",
152
- "140": "I-SYM|_|_",
153
- "141": "I-VERB|\u4ed6\u52d5\u8a5e|_",
154
- "142": "I-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
155
- "143": "I-VERB|\u5b8c\u5168\u52d5\u8a5e|_",
156
- "144": "I-VERB|\u683c\u52a9\u8a5e|_",
157
- "145": "I-VERB|\u81ea\u52d5\u8a5e|_",
158
- "146": "I-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_",
159
- "147": "I-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
160
- "148": "I-VERT|\u4ed6\u52d5\u8a5e|_",
161
- "149": "I-X|_|_",
162
- "150": "INTJ|\u9593\u6295\u8a5e|_",
163
- "151": "NOUN|\u4ee3\u540d\u8a5e|_",
164
- "152": "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
165
- "153": "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
166
- "154": "NOUN|\u540d\u8a5e|_",
167
- "155": "NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
168
- "156": "NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
169
- "157": "NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
170
- "158": "NOUN|\u56fa\u6709\u540d\u8a5e|_",
171
- "159": "NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
172
- "160": "NUM|\u6570\u8a5e|_",
173
- "161": "PART|\u4eba\u79f0\u63a5\u8f9e|_",
174
- "162": "PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
175
- "163": "PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
176
- "164": "PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
177
- "165": "PART|\u63a5\u5c3e\u8f9e|_",
178
- "166": "PART|\u63a5\u7d9a\u52a9\u8a5e|_",
179
- "167": "PART|\u63a5\u982d\u8f9e|_",
180
- "168": "PART|\u7d42\u52a9\u8a5e|_",
181
- "169": "PART|\u81ea\u52d5\u8a5e|_",
182
- "170": "PROPN|\u56fa\u6709\u540d\u8a5e|_",
183
- "171": "PUNCT|\u8a18\u53f7|_",
184
- "172": "SCONJ|\u4ed6\u52d5\u8a5e|_",
185
- "173": "SCONJ|\u526f\u8a5e|_",
186
- "174": "SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
187
- "175": "SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
188
- "176": "SCONJ|\u63a5\u7d9a\u8a5e|_",
189
- "177": "SCONJ|\u683c\u52a9\u8a5e|_",
190
- "178": "SCONJ|\u7d42\u52a9\u8a5e|_",
191
- "179": "SYM",
192
- "180": "SYM|_|_",
193
- "181": "VERB|\u4ed6\u52d5\u8a5e|_",
194
- "182": "VERB|\u4ed6\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
195
- "183": "VERB|\u4ed6\u52d5\u8a5e|_+PART|\u63a5\u5c3e\u8f9e|_",
196
- "184": "VERB|\u5b8c\u5168\u52d5\u8a5e|_",
197
- "185": "VERB|\u81ea\u52d5\u8a5e|_",
198
- "186": "VERB|\u81ea\u52d5\u8a5e|_+AUX|\u52a9\u52d5\u8a5e|_",
199
- "187": "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_",
200
- "188": "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
201
- "189": "VERB|\u81ea\u52d5\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_"
 
 
 
 
 
 
202
  },
203
  "initializer_range": 0.02,
204
  "intermediate_size": 3072,
@@ -218,181 +224,187 @@
218
  "B-ADP|\u683c\u52a9\u8a5e|_": 12,
219
  "B-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 13,
220
  "B-ADV|\u526f\u8a5e|_": 14,
221
- "B-ADV|\u9593\u6295\u8a5e|_": 15,
222
- "B-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 16,
223
- "B-AUX|\u52a9\u52d5\u8a5e|_": 17,
224
- "B-AUX|\u52a9\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 18,
225
- "B-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_": 19,
226
- "B-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 20,
227
- "B-CCONJ|\u63a5\u7d9a\u8a5e|_": 21,
228
- "B-DET|\u526f\u8a5e|_": 22,
229
- "B-DET|\u9023\u4f53\u8a5e|_": 23,
230
- "B-DET|\u9023\u4f53\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 24,
231
- "B-INTJ|\u9593\u6295\u8a5e|_": 25,
232
- "B-NOUN|\u4eba\u79f0\u63a5\u8f9e|_": 26,
233
- "B-NOUN|\u4ee3\u540d\u8a5e|_": 27,
234
- "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 28,
235
- "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 29,
236
- "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_": 30,
237
- "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 31,
238
- "B-NOUN|\u540d\u8a5e|_": 32,
239
- "B-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 33,
240
- "B-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_": 34,
241
- "B-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 35,
242
- "B-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": 36,
243
- "B-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 37,
244
- "B-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 38,
245
- "B-NOUN|\u56fa\u6709\u540d\u8a5e|_": 39,
246
- "B-NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 40,
247
- "B-NUM|\u6570\u8a5e|_": 41,
248
- "B-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_": 42,
249
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_": 43,
250
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 44,
251
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 45,
252
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 46,
253
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 47,
254
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_": 48,
255
- "B-PART|\u52a9\u52d5\u8a5e|_": 49,
256
- "B-PART|\u63a5\u5c3e\u8f9e|_": 50,
257
- "B-PART|\u63a5\u7d9a\u52a9\u8a5e|_": 51,
258
- "B-PART|\u63a5\u982d\u8f9e|_": 52,
259
- "B-PART|\u7d42\u52a9\u8a5e|_": 53,
260
- "B-PART|\u81ea\u52d5\u8a5e|_": 54,
261
- "B-PRON|\u4ee3\u540d\u8a5e|_": 55,
262
- "B-PROPN|\u56fa\u6709\u540d\u8a5e|_": 56,
263
- "B-PUNCT|\u8a18\u53f7|_": 57,
264
- "B-SCONJ|\u4ed6\u52d5\u8a5e|_": 58,
265
- "B-SCONJ|\u526f\u8a5e|_": 59,
266
- "B-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 60,
267
- "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 61,
268
- "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_": 62,
269
- "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+DET|\u9023\u4f53\u8a5e|_": 63,
270
- "B-SCONJ|\u63a5\u7d9a\u8a5e|_": 64,
271
- "B-SCONJ|\u683c\u52a9\u8a5e|_": 65,
272
- "B-SCONJ|\u7d42\u52a9\u8a5e|_": 66,
273
- "B-SYM|_|_": 67,
274
- "B-VERB|\u4ed6\u52d5\u8a5e|_": 68,
275
- "B-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 69,
276
- "B-VERB|\u5b8c\u5168\u52d5\u8a5e|_": 70,
277
- "B-VERB|\u683c\u52a9\u8a5e|_": 71,
278
- "B-VERB|\u81ea\u52d5\u8a5e|_": 72,
279
- "B-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_": 73,
280
- "B-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 74,
281
- "B-VERT|\u4ed6\u52d5\u8a5e|_": 75,
282
- "B-X|_|_": 76,
283
- "CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 77,
284
- "CCONJ|\u63a5\u7d9a\u8a5e|_": 78,
285
- "DET|\u9023\u4f53\u8a5e|_": 79,
286
- "DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_": 80,
287
- "DET|\u9023\u4f53\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": 81,
288
- "I-ADP|\u526f\u52a9\u8a5e|_": 82,
289
- "I-ADP|\u526f\u8a5e|_": 83,
290
- "I-ADP|\u5f8c\u7f6e\u526f\u8a5e|_": 84,
291
- "I-ADP|\u683c\u52a9\u8a5e|_": 85,
292
- "I-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 86,
293
- "I-ADV|\u526f\u8a5e|_": 87,
294
- "I-ADV|\u9593\u6295\u8a5e|_": 88,
295
- "I-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 89,
296
- "I-AUX|\u52a9\u52d5\u8a5e|_": 90,
297
- "I-AUX|\u52a9\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 91,
298
- "I-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_": 92,
299
- "I-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 93,
300
- "I-CCONJ|\u63a5\u7d9a\u8a5e|_": 94,
301
- "I-DET|\u526f\u8a5e|_": 95,
302
- "I-DET|\u9023\u4f53\u8a5e|_": 96,
303
- "I-DET|\u9023\u4f53\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 97,
304
- "I-INTJ|\u9593\u6295\u8a5e|_": 98,
305
- "I-NOUN|\u4eba\u79f0\u63a5\u8f9e|_": 99,
306
- "I-NOUN|\u4ee3\u540d\u8a5e|_": 100,
307
- "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 101,
308
- "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 102,
309
- "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_": 103,
310
- "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 104,
311
- "I-NOUN|\u540d\u8a5e|_": 105,
312
- "I-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 106,
313
- "I-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_": 107,
314
- "I-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 108,
315
- "I-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": 109,
316
- "I-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 110,
317
- "I-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 111,
318
- "I-NOUN|\u56fa\u6709\u540d\u8a5e|_": 112,
319
- "I-NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 113,
320
- "I-NUM|\u6570\u8a5e|_": 114,
321
- "I-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_": 115,
322
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_": 116,
323
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 117,
324
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 118,
325
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 119,
326
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 120,
327
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_": 121,
328
- "I-PART|\u52a9\u52d5\u8a5e|_": 122,
329
- "I-PART|\u63a5\u5c3e\u8f9e|_": 123,
330
- "I-PART|\u63a5\u7d9a\u52a9\u8a5e|_": 124,
331
- "I-PART|\u63a5\u982d\u8f9e|_": 125,
332
- "I-PART|\u7d42\u52a9\u8a5e|_": 126,
333
- "I-PART|\u81ea\u52d5\u8a5e|_": 127,
334
- "I-PRON|\u4ee3\u540d\u8a5e|_": 128,
335
- "I-PROPN|\u56fa\u6709\u540d\u8a5e|_": 129,
336
- "I-PUNCT|\u8a18\u53f7|_": 130,
337
- "I-SCONJ|\u4ed6\u52d5\u8a5e|_": 131,
338
- "I-SCONJ|\u526f\u8a5e|_": 132,
339
- "I-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 133,
340
- "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 134,
341
- "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_": 135,
342
- "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+DET|\u9023\u4f53\u8a5e|_": 136,
343
- "I-SCONJ|\u63a5\u7d9a\u8a5e|_": 137,
344
- "I-SCONJ|\u683c\u52a9\u8a5e|_": 138,
345
- "I-SCONJ|\u7d42\u52a9\u8a5e|_": 139,
346
- "I-SYM|_|_": 140,
347
- "I-VERB|\u4ed6\u52d5\u8a5e|_": 141,
348
- "I-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 142,
349
- "I-VERB|\u5b8c\u5168\u52d5\u8a5e|_": 143,
350
- "I-VERB|\u683c\u52a9\u8a5e|_": 144,
351
- "I-VERB|\u81ea\u52d5\u8a5e|_": 145,
352
- "I-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_": 146,
353
- "I-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 147,
354
- "I-VERT|\u4ed6\u52d5\u8a5e|_": 148,
355
- "I-X|_|_": 149,
356
- "INTJ|\u9593\u6295\u8a5e|_": 150,
357
- "NOUN|\u4ee3\u540d\u8a5e|_": 151,
358
- "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 152,
359
- "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 153,
360
- "NOUN|\u540d\u8a5e|_": 154,
361
- "NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 155,
362
- "NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 156,
363
- "NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 157,
364
- "NOUN|\u56fa\u6709\u540d\u8a5e|_": 158,
365
- "NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 159,
366
- "NUM|\u6570\u8a5e|_": 160,
367
- "PART|\u4eba\u79f0\u63a5\u8f9e|_": 161,
368
- "PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 162,
369
- "PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 163,
370
- "PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 164,
371
- "PART|\u63a5\u5c3e\u8f9e|_": 165,
372
- "PART|\u63a5\u7d9a\u52a9\u8a5e|_": 166,
373
- "PART|\u63a5\u982d\u8f9e|_": 167,
374
- "PART|\u7d42\u52a9\u8a5e|_": 168,
375
- "PART|\u81ea\u52d5\u8a5e|_": 169,
376
- "PROPN|\u56fa\u6709\u540d\u8a5e|_": 170,
377
- "PUNCT|\u8a18\u53f7|_": 171,
378
- "SCONJ|\u4ed6\u52d5\u8a5e|_": 172,
379
- "SCONJ|\u526f\u8a5e|_": 173,
380
- "SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 174,
381
- "SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 175,
382
- "SCONJ|\u63a5\u7d9a\u8a5e|_": 176,
383
- "SCONJ|\u683c\u52a9\u8a5e|_": 177,
384
- "SCONJ|\u7d42\u52a9\u8a5e|_": 178,
385
- "SYM": 179,
386
- "SYM|_|_": 180,
387
- "VERB|\u4ed6\u52d5\u8a5e|_": 181,
388
- "VERB|\u4ed6\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 182,
389
- "VERB|\u4ed6\u52d5\u8a5e|_+PART|\u63a5\u5c3e\u8f9e|_": 183,
390
- "VERB|\u5b8c\u5168\u52d5\u8a5e|_": 184,
391
- "VERB|\u81ea\u52d5\u8a5e|_": 185,
392
- "VERB|\u81ea\u52d5\u8a5e|_+AUX|\u52a9\u52d5\u8a5e|_": 186,
393
- "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_": 187,
394
- "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 188,
395
- "VERB|\u81ea\u52d5\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": 189
 
 
 
 
 
 
396
  },
397
  "layer_norm_eps": 1e-07,
398
  "max_position_embeddings": 512,
@@ -419,6 +431,18 @@
419
  "be"
420
  ]
421
  },
 
 
 
 
 
 
 
 
 
 
 
 
422
  "AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": {
423
  "nep": [
424
  "ne",
@@ -452,6 +476,10 @@
452
  ]
453
  },
454
  "DET|\u9023\u4f53\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": {
 
 
 
 
455
  "toambe": [
456
  "toam",
457
  "be"
@@ -513,6 +541,10 @@
513
  "oro",
514
  "wa"
515
  ],
 
 
 
 
516
  "orowano": [
517
  "oro",
518
  "wano"
@@ -567,6 +599,12 @@
567
  "kushte"
568
  ]
569
  },
 
 
 
 
 
 
570
  "NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": {
571
  "Kunneiwano": [
572
  "Kunnei",
@@ -591,6 +629,12 @@
591
  "ta ne"
592
  ]
593
  },
 
 
 
 
 
 
594
  "NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": {
595
  "Harikisam": [
596
  "Hariki",
@@ -610,10 +654,6 @@
610
  ]
611
  },
612
  "NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": {
613
- "Shirokanipe": [
614
- "Shirokani",
615
- "pe"
616
- ],
617
  "Tambet aaye": [
618
  "Tambe",
619
  "t aaye"
@@ -625,10 +665,6 @@
625
  "kamuinish": [
626
  "kamui",
627
  "nish"
628
- ],
629
- "konkanipe": [
630
- "konkani",
631
- "pe"
632
  ]
633
  },
634
  "NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": {
@@ -681,6 +717,12 @@
681
  "to"
682
  ]
683
  },
 
 
 
 
 
 
684
  "PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": {
685
  "chine": [
686
  "chi",
@@ -836,12 +878,6 @@
836
  "an",
837
  "akanakne"
838
  ]
839
- },
840
- "VERB|\u81ea\u52d5\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": {
841
- "ranran": [
842
- "ran",
843
- "ran"
844
- ]
845
  }
846
  }
847
  },
 
24
  "12": "B-ADP|\u683c\u52a9\u8a5e|_",
25
  "13": "B-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
26
  "14": "B-ADV|\u526f\u8a5e|_",
27
+ "15": "B-ADV|\u526f\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
28
+ "16": "B-ADV|\u526f\u8a5e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
29
+ "17": "B-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
30
+ "18": "B-AUX|\u52a9\u52d5\u8a5e|_",
31
+ "19": "B-AUX|\u52a9\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
32
+ "20": "B-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_",
33
+ "21": "B-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
34
+ "22": "B-CCONJ|\u63a5\u7d9a\u8a5e|_",
35
+ "23": "B-DET|\u526f\u8a5e|_",
36
+ "24": "B-DET|\u9023\u4f53\u8a5e|_",
37
+ "25": "B-DET|\u9023\u4f53\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
38
+ "26": "B-INTJ|\u9593\u6295\u8a5e|_",
39
+ "27": "B-NOUN|\u4eba\u79f0\u63a5\u8f9e|_",
40
+ "28": "B-NOUN|\u4ee3\u540d\u8a5e|_",
41
+ "29": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
42
+ "30": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
43
+ "31": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_",
44
+ "32": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
45
+ "33": "B-NOUN|\u540d\u8a5e|_",
46
+ "34": "B-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
47
+ "35": "B-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_",
48
+ "36": "B-NOUN|\u540d\u8a5e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
49
+ "37": "B-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
50
+ "38": "B-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_",
51
+ "39": "B-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
52
+ "40": "B-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
53
+ "41": "B-NOUN|\u56fa\u6709\u540d\u8a5e|_",
54
+ "42": "B-NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
55
+ "43": "B-NUM|\u6570\u8a5e|_",
56
+ "44": "B-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_",
57
+ "45": "B-NUM|\u6570\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
58
+ "46": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_",
59
+ "47": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
60
+ "48": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
61
+ "49": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
62
+ "50": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
63
+ "51": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_",
64
+ "52": "B-PART|\u52a9\u52d5\u8a5e|_",
65
+ "53": "B-PART|\u63a5\u5c3e\u8f9e|_",
66
+ "54": "B-PART|\u63a5\u7d9a\u52a9\u8a5e|_",
67
+ "55": "B-PART|\u63a5\u982d\u8f9e|_",
68
+ "56": "B-PART|\u7d42\u52a9\u8a5e|_",
69
+ "57": "B-PART|\u81ea\u52d5\u8a5e|_",
70
+ "58": "B-PRON|\u4ee3\u540d\u8a5e|_",
71
+ "59": "B-PROPN|\u56fa\u6709\u540d\u8a5e|_",
72
+ "60": "B-PUNCT|\u8a18\u53f7|_",
73
+ "61": "B-SCONJ|\u4ed6\u52d5\u8a5e|_",
74
+ "62": "B-SCONJ|\u526f\u8a5e|_",
75
+ "63": "B-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
76
+ "64": "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
77
+ "65": "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_",
78
+ "66": "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+DET|\u9023\u4f53\u8a5e|_",
79
+ "67": "B-SCONJ|\u63a5\u7d9a\u8a5e|_",
80
+ "68": "B-SCONJ|\u683c\u52a9\u8a5e|_",
81
+ "69": "B-SCONJ|\u7d42\u52a9\u8a5e|_",
82
+ "70": "B-SYM|_|_",
83
+ "71": "B-VERB|\u4ed6\u52d5\u8a5e|_",
84
+ "72": "B-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
85
+ "73": "B-VERB|\u5b8c\u5168\u52d5\u8a5e|_",
86
+ "74": "B-VERB|\u683c\u52a9\u8a5e|_",
87
+ "75": "B-VERB|\u81ea\u52d5\u8a5e|_",
88
+ "76": "B-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_",
89
+ "77": "B-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
90
+ "78": "B-VERT|\u4ed6\u52d5\u8a5e|_",
91
+ "79": "B-X|_|_",
92
+ "80": "CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
93
+ "81": "CCONJ|\u63a5\u7d9a\u8a5e|_",
94
+ "82": "DET|\u9023\u4f53\u8a5e|_",
95
+ "83": "DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_",
96
+ "84": "DET|\u9023\u4f53\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_",
97
+ "85": "I-ADP|\u526f\u52a9\u8a5e|_",
98
+ "86": "I-ADP|\u526f\u8a5e|_",
99
+ "87": "I-ADP|\u5f8c\u7f6e\u526f\u8a5e|_",
100
+ "88": "I-ADP|\u683c\u52a9\u8a5e|_",
101
+ "89": "I-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
102
+ "90": "I-ADV|\u526f\u8a5e|_",
103
+ "91": "I-ADV|\u526f\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
104
+ "92": "I-ADV|\u526f\u8a5e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
105
+ "93": "I-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
106
+ "94": "I-AUX|\u52a9\u52d5\u8a5e|_",
107
+ "95": "I-AUX|\u52a9\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
108
+ "96": "I-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_",
109
+ "97": "I-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
110
+ "98": "I-CCONJ|\u63a5\u7d9a\u8a5e|_",
111
+ "99": "I-DET|\u526f\u8a5e|_",
112
+ "100": "I-DET|\u9023\u4f53\u8a5e|_",
113
+ "101": "I-DET|\u9023\u4f53\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
114
+ "102": "I-INTJ|\u9593\u6295\u8a5e|_",
115
+ "103": "I-NOUN|\u4eba\u79f0\u63a5\u8f9e|_",
116
+ "104": "I-NOUN|\u4ee3\u540d\u8a5e|_",
117
+ "105": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
118
+ "106": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
119
+ "107": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_",
120
+ "108": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
121
+ "109": "I-NOUN|\u540d\u8a5e|_",
122
+ "110": "I-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
123
+ "111": "I-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_",
124
+ "112": "I-NOUN|\u540d\u8a5e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
125
+ "113": "I-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
126
+ "114": "I-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_",
127
+ "115": "I-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
128
+ "116": "I-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
129
+ "117": "I-NOUN|\u56fa\u6709\u540d\u8a5e|_",
130
+ "118": "I-NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
131
+ "119": "I-NUM|\u6570\u8a5e|_",
132
+ "120": "I-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_",
133
+ "121": "I-NUM|\u6570\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
134
+ "122": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_",
135
+ "123": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
136
+ "124": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
137
+ "125": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
138
+ "126": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
139
+ "127": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_",
140
+ "128": "I-PART|\u52a9\u52d5\u8a5e|_",
141
+ "129": "I-PART|\u63a5\u5c3e\u8f9e|_",
142
+ "130": "I-PART|\u63a5\u7d9a\u52a9\u8a5e|_",
143
+ "131": "I-PART|\u63a5\u982d\u8f9e|_",
144
+ "132": "I-PART|\u7d42\u52a9\u8a5e|_",
145
+ "133": "I-PART|\u81ea\u52d5\u8a5e|_",
146
+ "134": "I-PRON|\u4ee3\u540d\u8a5e|_",
147
+ "135": "I-PROPN|\u56fa\u6709\u540d\u8a5e|_",
148
+ "136": "I-PUNCT|\u8a18\u53f7|_",
149
+ "137": "I-SCONJ|\u4ed6\u52d5\u8a5e|_",
150
+ "138": "I-SCONJ|\u526f\u8a5e|_",
151
+ "139": "I-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
152
+ "140": "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
153
+ "141": "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_",
154
+ "142": "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+DET|\u9023\u4f53\u8a5e|_",
155
+ "143": "I-SCONJ|\u63a5\u7d9a\u8a5e|_",
156
+ "144": "I-SCONJ|\u683c\u52a9\u8a5e|_",
157
+ "145": "I-SCONJ|\u7d42\u52a9\u8a5e|_",
158
+ "146": "I-SYM|_|_",
159
+ "147": "I-VERB|\u4ed6\u52d5\u8a5e|_",
160
+ "148": "I-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
161
+ "149": "I-VERB|\u5b8c\u5168\u52d5\u8a5e|_",
162
+ "150": "I-VERB|\u683c\u52a9\u8a5e|_",
163
+ "151": "I-VERB|\u81ea\u52d5\u8a5e|_",
164
+ "152": "I-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_",
165
+ "153": "I-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
166
+ "154": "I-VERT|\u4ed6\u52d5\u8a5e|_",
167
+ "155": "I-X|_|_",
168
+ "156": "INTJ|\u9593\u6295\u8a5e|_",
169
+ "157": "NOUN|\u4ee3\u540d\u8a5e|_",
170
+ "158": "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
171
+ "159": "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
172
+ "160": "NOUN|\u540d\u8a5e|_",
173
+ "161": "NOUN|\u540d\u8a5e|_+ADP|\u526f\u52a9\u8a5e|_",
174
+ "162": "NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
175
+ "163": "NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
176
+ "164": "NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
177
+ "165": "NOUN|\u56fa\u6709\u540d\u8a5e|_",
178
+ "166": "NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
179
+ "167": "NUM|\u6570\u8a5e|_",
180
+ "168": "PART|\u4eba\u79f0\u63a5\u8f9e|_",
181
+ "169": "PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
182
+ "170": "PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
183
+ "171": "PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
184
+ "172": "PART|\u63a5\u5c3e\u8f9e|_",
185
+ "173": "PART|\u63a5\u7d9a\u52a9\u8a5e|_",
186
+ "174": "PART|\u63a5\u982d\u8f9e|_",
187
+ "175": "PART|\u7d42\u52a9\u8a5e|_",
188
+ "176": "PART|\u81ea\u52d5\u8a5e|_",
189
+ "177": "PROPN|\u56fa\u6709\u540d\u8a5e|_",
190
+ "178": "PUNCT|\u8a18\u53f7|_",
191
+ "179": "SCONJ|\u4ed6\u52d5\u8a5e|_",
192
+ "180": "SCONJ|\u526f\u8a5e|_",
193
+ "181": "SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
194
+ "182": "SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
195
+ "183": "SCONJ|\u63a5\u7d9a\u8a5e|_",
196
+ "184": "SCONJ|\u683c\u52a9\u8a5e|_",
197
+ "185": "SCONJ|\u7d42\u52a9\u8a5e|_",
198
+ "186": "SYM",
199
+ "187": "SYM|_|_",
200
+ "188": "VERB|\u4ed6\u52d5\u8a5e|_",
201
+ "189": "VERB|\u4ed6\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
202
+ "190": "VERB|\u4ed6\u52d5\u8a5e|_+PART|\u63a5\u5c3e\u8f9e|_",
203
+ "191": "VERB|\u5b8c\u5168\u52d5\u8a5e|_",
204
+ "192": "VERB|\u81ea\u52d5\u8a5e|_",
205
+ "193": "VERB|\u81ea\u52d5\u8a5e|_+AUX|\u52a9\u52d5\u8a5e|_",
206
+ "194": "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_",
207
+ "195": "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_"
208
  },
209
  "initializer_range": 0.02,
210
  "intermediate_size": 3072,
 
224
  "B-ADP|\u683c\u52a9\u8a5e|_": 12,
225
  "B-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 13,
226
  "B-ADV|\u526f\u8a5e|_": 14,
227
+ "B-ADV|\u526f\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 15,
228
+ "B-ADV|\u526f\u8a5e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 16,
229
+ "B-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 17,
230
+ "B-AUX|\u52a9\u52d5\u8a5e|_": 18,
231
+ "B-AUX|\u52a9\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 19,
232
+ "B-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_": 20,
233
+ "B-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 21,
234
+ "B-CCONJ|\u63a5\u7d9a\u8a5e|_": 22,
235
+ "B-DET|\u526f\u8a5e|_": 23,
236
+ "B-DET|\u9023\u4f53\u8a5e|_": 24,
237
+ "B-DET|\u9023\u4f53\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 25,
238
+ "B-INTJ|\u9593\u6295\u8a5e|_": 26,
239
+ "B-NOUN|\u4eba\u79f0\u63a5\u8f9e|_": 27,
240
+ "B-NOUN|\u4ee3\u540d\u8a5e|_": 28,
241
+ "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 29,
242
+ "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 30,
243
+ "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_": 31,
244
+ "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 32,
245
+ "B-NOUN|\u540d\u8a5e|_": 33,
246
+ "B-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 34,
247
+ "B-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_": 35,
248
+ "B-NOUN|\u540d\u8a5e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 36,
249
+ "B-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 37,
250
+ "B-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": 38,
251
+ "B-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 39,
252
+ "B-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 40,
253
+ "B-NOUN|\u56fa\u6709\u540d\u8a5e|_": 41,
254
+ "B-NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 42,
255
+ "B-NUM|\u6570\u8a5e|_": 43,
256
+ "B-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_": 44,
257
+ "B-NUM|\u6570\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 45,
258
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_": 46,
259
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 47,
260
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 48,
261
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 49,
262
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 50,
263
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_": 51,
264
+ "B-PART|\u52a9\u52d5\u8a5e|_": 52,
265
+ "B-PART|\u63a5\u5c3e\u8f9e|_": 53,
266
+ "B-PART|\u63a5\u7d9a\u52a9\u8a5e|_": 54,
267
+ "B-PART|\u63a5\u982d\u8f9e|_": 55,
268
+ "B-PART|\u7d42\u52a9\u8a5e|_": 56,
269
+ "B-PART|\u81ea\u52d5\u8a5e|_": 57,
270
+ "B-PRON|\u4ee3\u540d\u8a5e|_": 58,
271
+ "B-PROPN|\u56fa\u6709\u540d\u8a5e|_": 59,
272
+ "B-PUNCT|\u8a18\u53f7|_": 60,
273
+ "B-SCONJ|\u4ed6\u52d5\u8a5e|_": 61,
274
+ "B-SCONJ|\u526f\u8a5e|_": 62,
275
+ "B-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 63,
276
+ "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 64,
277
+ "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_": 65,
278
+ "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+DET|\u9023\u4f53\u8a5e|_": 66,
279
+ "B-SCONJ|\u63a5\u7d9a\u8a5e|_": 67,
280
+ "B-SCONJ|\u683c\u52a9\u8a5e|_": 68,
281
+ "B-SCONJ|\u7d42\u52a9\u8a5e|_": 69,
282
+ "B-SYM|_|_": 70,
283
+ "B-VERB|\u4ed6\u52d5\u8a5e|_": 71,
284
+ "B-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 72,
285
+ "B-VERB|\u5b8c\u5168\u52d5\u8a5e|_": 73,
286
+ "B-VERB|\u683c\u52a9\u8a5e|_": 74,
287
+ "B-VERB|\u81ea\u52d5\u8a5e|_": 75,
288
+ "B-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_": 76,
289
+ "B-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 77,
290
+ "B-VERT|\u4ed6\u52d5\u8a5e|_": 78,
291
+ "B-X|_|_": 79,
292
+ "CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 80,
293
+ "CCONJ|\u63a5\u7d9a\u8a5e|_": 81,
294
+ "DET|\u9023\u4f53\u8a5e|_": 82,
295
+ "DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_": 83,
296
+ "DET|\u9023\u4f53\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": 84,
297
+ "I-ADP|\u526f\u52a9\u8a5e|_": 85,
298
+ "I-ADP|\u526f\u8a5e|_": 86,
299
+ "I-ADP|\u5f8c\u7f6e\u526f\u8a5e|_": 87,
300
+ "I-ADP|\u683c\u52a9\u8a5e|_": 88,
301
+ "I-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 89,
302
+ "I-ADV|\u526f\u8a5e|_": 90,
303
+ "I-ADV|\u526f\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 91,
304
+ "I-ADV|\u526f\u8a5e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 92,
305
+ "I-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 93,
306
+ "I-AUX|\u52a9\u52d5\u8a5e|_": 94,
307
+ "I-AUX|\u52a9\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 95,
308
+ "I-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_": 96,
309
+ "I-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 97,
310
+ "I-CCONJ|\u63a5\u7d9a\u8a5e|_": 98,
311
+ "I-DET|\u526f\u8a5e|_": 99,
312
+ "I-DET|\u9023\u4f53\u8a5e|_": 100,
313
+ "I-DET|\u9023\u4f53\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 101,
314
+ "I-INTJ|\u9593\u6295\u8a5e|_": 102,
315
+ "I-NOUN|\u4eba\u79f0\u63a5\u8f9e|_": 103,
316
+ "I-NOUN|\u4ee3\u540d\u8a5e|_": 104,
317
+ "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 105,
318
+ "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 106,
319
+ "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_": 107,
320
+ "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 108,
321
+ "I-NOUN|\u540d\u8a5e|_": 109,
322
+ "I-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 110,
323
+ "I-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_": 111,
324
+ "I-NOUN|\u540d\u8a5e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 112,
325
+ "I-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 113,
326
+ "I-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": 114,
327
+ "I-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 115,
328
+ "I-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 116,
329
+ "I-NOUN|\u56fa\u6709\u540d\u8a5e|_": 117,
330
+ "I-NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 118,
331
+ "I-NUM|\u6570\u8a5e|_": 119,
332
+ "I-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_": 120,
333
+ "I-NUM|\u6570\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 121,
334
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_": 122,
335
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 123,
336
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 124,
337
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 125,
338
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 126,
339
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_": 127,
340
+ "I-PART|\u52a9\u52d5\u8a5e|_": 128,
341
+ "I-PART|\u63a5\u5c3e\u8f9e|_": 129,
342
+ "I-PART|\u63a5\u7d9a\u52a9\u8a5e|_": 130,
343
+ "I-PART|\u63a5\u982d\u8f9e|_": 131,
344
+ "I-PART|\u7d42\u52a9\u8a5e|_": 132,
345
+ "I-PART|\u81ea\u52d5\u8a5e|_": 133,
346
+ "I-PRON|\u4ee3\u540d\u8a5e|_": 134,
347
+ "I-PROPN|\u56fa\u6709\u540d\u8a5e|_": 135,
348
+ "I-PUNCT|\u8a18\u53f7|_": 136,
349
+ "I-SCONJ|\u4ed6\u52d5\u8a5e|_": 137,
350
+ "I-SCONJ|\u526f\u8a5e|_": 138,
351
+ "I-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 139,
352
+ "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 140,
353
+ "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_": 141,
354
+ "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+DET|\u9023\u4f53\u8a5e|_": 142,
355
+ "I-SCONJ|\u63a5\u7d9a\u8a5e|_": 143,
356
+ "I-SCONJ|\u683c\u52a9\u8a5e|_": 144,
357
+ "I-SCONJ|\u7d42\u52a9\u8a5e|_": 145,
358
+ "I-SYM|_|_": 146,
359
+ "I-VERB|\u4ed6\u52d5\u8a5e|_": 147,
360
+ "I-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 148,
361
+ "I-VERB|\u5b8c\u5168\u52d5\u8a5e|_": 149,
362
+ "I-VERB|\u683c\u52a9\u8a5e|_": 150,
363
+ "I-VERB|\u81ea\u52d5\u8a5e|_": 151,
364
+ "I-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_": 152,
365
+ "I-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 153,
366
+ "I-VERT|\u4ed6\u52d5\u8a5e|_": 154,
367
+ "I-X|_|_": 155,
368
+ "INTJ|\u9593\u6295\u8a5e|_": 156,
369
+ "NOUN|\u4ee3\u540d\u8a5e|_": 157,
370
+ "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 158,
371
+ "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 159,
372
+ "NOUN|\u540d\u8a5e|_": 160,
373
+ "NOUN|\u540d\u8a5e|_+ADP|\u526f\u52a9\u8a5e|_": 161,
374
+ "NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 162,
375
+ "NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 163,
376
+ "NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 164,
377
+ "NOUN|\u56fa\u6709\u540d\u8a5e|_": 165,
378
+ "NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 166,
379
+ "NUM|\u6570\u8a5e|_": 167,
380
+ "PART|\u4eba\u79f0\u63a5\u8f9e|_": 168,
381
+ "PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 169,
382
+ "PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 170,
383
+ "PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 171,
384
+ "PART|\u63a5\u5c3e\u8f9e|_": 172,
385
+ "PART|\u63a5\u7d9a\u52a9\u8a5e|_": 173,
386
+ "PART|\u63a5\u982d\u8f9e|_": 174,
387
+ "PART|\u7d42\u52a9\u8a5e|_": 175,
388
+ "PART|\u81ea\u52d5\u8a5e|_": 176,
389
+ "PROPN|\u56fa\u6709\u540d\u8a5e|_": 177,
390
+ "PUNCT|\u8a18\u53f7|_": 178,
391
+ "SCONJ|\u4ed6\u52d5\u8a5e|_": 179,
392
+ "SCONJ|\u526f\u8a5e|_": 180,
393
+ "SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 181,
394
+ "SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 182,
395
+ "SCONJ|\u63a5\u7d9a\u8a5e|_": 183,
396
+ "SCONJ|\u683c\u52a9\u8a5e|_": 184,
397
+ "SCONJ|\u7d42\u52a9\u8a5e|_": 185,
398
+ "SYM": 186,
399
+ "SYM|_|_": 187,
400
+ "VERB|\u4ed6\u52d5\u8a5e|_": 188,
401
+ "VERB|\u4ed6\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 189,
402
+ "VERB|\u4ed6\u52d5\u8a5e|_+PART|\u63a5\u5c3e\u8f9e|_": 190,
403
+ "VERB|\u5b8c\u5168\u52d5\u8a5e|_": 191,
404
+ "VERB|\u81ea\u52d5\u8a5e|_": 192,
405
+ "VERB|\u81ea\u52d5\u8a5e|_+AUX|\u52a9\u52d5\u8a5e|_": 193,
406
+ "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_": 194,
407
+ "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 195
408
  },
409
  "layer_norm_eps": 1e-07,
410
  "max_position_embeddings": 512,
 
431
  "be"
432
  ]
433
  },
434
+ "ADV|\u526f\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": {
435
+ "arashuine": [
436
+ "arashui",
437
+ "ne"
438
+ ]
439
+ },
440
+ "ADV|\u526f\u8a5e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": {
441
+ "arashuine": [
442
+ "arashui",
443
+ "ne"
444
+ ]
445
+ },
446
  "AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": {
447
  "nep": [
448
  "ne",
 
476
  ]
477
  },
478
  "DET|\u9023\u4f53\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": {
479
+ "Toambe": [
480
+ "Toam",
481
+ "be"
482
+ ],
483
  "toambe": [
484
  "toam",
485
  "be"
 
541
  "oro",
542
  "wa"
543
  ],
544
+ "orowa no": [
545
+ "oro",
546
+ "wa no"
547
+ ],
548
  "orowano": [
549
  "oro",
550
  "wano"
 
599
  "kushte"
600
  ]
601
  },
602
+ "NOUN|\u540d\u8a5e|_+ADP|\u526f\u52a9\u8a5e|_": {
603
+ "utarorke": [
604
+ "utar",
605
+ "orke"
606
+ ]
607
+ },
608
  "NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": {
609
  "Kunneiwano": [
610
  "Kunnei",
 
629
  "ta ne"
630
  ]
631
  },
632
+ "NOUN|\u540d\u8a5e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": {
633
+ "ikinne": [
634
+ "ikin",
635
+ "ne"
636
+ ]
637
+ },
638
  "NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": {
639
  "Harikisam": [
640
  "Hariki",
 
654
  ]
655
  },
656
  "NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": {
 
 
 
 
657
  "Tambet aaye": [
658
  "Tambe",
659
  "t aaye"
 
665
  "kamuinish": [
666
  "kamui",
667
  "nish"
 
 
 
 
668
  ]
669
  },
670
  "NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": {
 
717
  "to"
718
  ]
719
  },
720
+ "NUM|\u6570\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": {
721
+ "wambe": [
722
+ "wam",
723
+ "be"
724
+ ]
725
+ },
726
  "PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": {
727
  "chine": [
728
  "chi",
 
878
  "an",
879
  "akanakne"
880
  ]
 
 
 
 
 
 
881
  }
882
  }
883
  },
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d30e40c2875580122dbd6fb407dc48e660ed964cfbddfc5224ce7aeada760f2c
3
- size 419957900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5305c503beab7d30b8827a74a76b01b6f478dd2db8cd0ac56e93731f7dfc844f
3
+ size 419976396
supar.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ff6d37537a801037592c805f8ccd4dd19c93f7fdf454d352385dfe99dd4ece4
3
- size 464655012
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916150b599b5923157a733b9064dbc625ac77be7b463928104fd8387707c9612
3
+ size 464665640
tokenizer.json CHANGED
@@ -779,6 +779,20 @@
779
  },
780
  "content": ","
781
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
782
  {
783
  "type": "Replace",
784
  "pattern": {
 
779
  },
780
  "content": ","
781
  },
782
+ {
783
+ "type": "Replace",
784
+ "pattern": {
785
+ "String": "“"
786
+ },
787
+ "content": "\""
788
+ },
789
+ {
790
+ "type": "Replace",
791
+ "pattern": {
792
+ "String": "”"
793
+ },
794
+ "content": "\""
795
+ },
796
  {
797
  "type": "Replace",
798
  "pattern": {