Hugging Face's logo

KoichiYasuoka
/
modernbert-base-russian-ud-embeds

Token Classification
PyTorch
Russian
modernbert
russian
pos
dependency-parsing
Model card Files Community
2
KoichiYasuoka commited on
Commit
643c1b2
·
1 Parent(s): 53e453c

initial release

Browse files
Files changed (8) hide show
  1. README.md +29 -0
  2. config.json +0 -0
  3. maker.py +115 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +46 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +954 -0
  8. ud.py +150 -0
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - "ru"
4
+ tags:
5
+ - "russian"
6
+ - "token-classification"
7
+ - "pos"
8
+ - "dependency-parsing"
9
+ base_model: deepvk/RuModernBERT-base
10
+ datasets:
11
+ - "universal_dependencies"
12
+ license: "apache-2.0"
13
+ pipeline_tag: "token-classification"
14
+ ---
15
+
16
+ # modernbert-base-russian-ud-embeds
17
+
18
+ ## Model Description
19
+
20
+ This is a ModernBERT model for POS-tagging and dependency-parsing, derived from [RuModernBERT-base](https://huggingface.co/deepvk/RuModernBERT-base).
21
+
22
+ ## How to Use
23
+
24
+ ```py
25
+ from transformers import pipeline
26
+ nlp=pipeline("universal-dependencies","KoichiYasuoka/modernbert-base-russian-ud-embeds",trust_remote_code=True)
27
+ print(nlp("Москва слезам не верила, а верила любви."))
28
+ ```
29
+
config.json ADDED
The diff for this file is too large to render. See raw diff
 
maker.py ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #! /usr/bin/python3
2
+ import os
3
+ src="deepvk/RuModernBERT-base"
4
+ tgt="KoichiYasuoka/modernbert-base-russian-ud-embeds"
5
+ url="https://github.com/UniversalDependencies/UD_Russian-"
6
+ for e in ["Taiga","SynTagRus","GSD","Poetry"]:
7
+ u=url+e
8
+ d=os.path.basename(u)
9
+ os.system("test -d "+d+" || git clone --depth=1 "+u)
10
+ os.system("for F in train dev test ; do cat UD_Russian-*/*-$F*.conllu > $F.conllu ; done")
11
+ class UDEmbedsDataset(object):
12
+ def __init__(self,conllu,tokenizer,embeddings=None):
13
+ self.conllu=open(conllu,"r",encoding="utf-8")
14
+ self.tokenizer=tokenizer
15
+ self.embeddings=embeddings
16
+ self.seeks=[0]
17
+ label=set(["SYM","SYM.","SYM|_"])
18
+ dep=set()
19
+ s=self.conllu.readline()
20
+ while s!="":
21
+ if s=="\n":
22
+ self.seeks.append(self.conllu.tell())
23
+ else:
24
+ w=s.split("\t")
25
+ if len(w)==10:
26
+ if w[0].isdecimal():
27
+ p=w[3]
28
+ q="" if w[5]=="_" else "|"+w[5]
29
+ d=("|" if w[6]=="0" else "|l-" if int(w[0])<int(w[6]) else "|r-")+w[7]
30
+ for k in [p,p+".","B-"+p,"B-"+p+".","I-"+p,"I-"+p+".",p+q+"|_",p+q+d]:
31
+ label.add(k)
32
+ s=self.conllu.readline()
33
+ self.label2id={l:i for i,l in enumerate(sorted(label))}
34
+ def __call__(*args):
35
+ lid={l:i for i,l in enumerate(sorted(set(sum([list(t.label2id) for t in args],[]))))}
36
+ for t in args:
37
+ t.label2id=lid
38
+ return lid
39
+ def __del__(self):
40
+ self.conllu.close()
41
+ __len__=lambda self:(len(self.seeks)-1)*2
42
+ def __getitem__(self,i):
43
+ self.conllu.seek(self.seeks[int(i/2)])
44
+ z,c,t,s=i%2,[],[""],False
45
+ while t[0]!="\n":
46
+ t=self.conllu.readline().split("\t")
47
+ if len(t)==10 and t[0].isdecimal():
48
+ if s:
49
+ t[1]=" "+t[1]
50
+ c.append(t)
51
+ s=t[9].find("SpaceAfter=No")<0
52
+ x=[True if t[6]=="0" or int(t[6])>j or sum([1 if int(c[i][6])==j+1 else 0 for i in range(j+1,len(c))])>0 else False for j,t in enumerate(c)]
53
+ v=self.tokenizer([t[1] for t in c],add_special_tokens=False)["input_ids"]
54
+ if z==0:
55
+ ids,upos=[self.tokenizer.cls_token_id],["SYM."]
56
+ for i,(j,k) in enumerate(zip(v,c)):
57
+ if j==[]:
58
+ j=[self.tokenizer.unk_token_id]
59
+ p=k[3] if x[i] else k[3]+"."
60
+ ids+=j
61
+ upos+=[p] if len(j)==1 else ["B-"+p]+["I-"+p]*(len(j)-1)
62
+ ids.append(self.tokenizer.sep_token_id)
63
+ upos.append("SYM.")
64
+ emb=self.embeddings
65
+ else:
66
+ import torch
67
+ if len(x)<127:
68
+ x=[True]*len(x)
69
+ w=(len(x)+2)*(len(x)+1)/2
70
+ else:
71
+ w=sum([len(x)-i+1 if b else 0 for i,b in enumerate(x)])+1
72
+ for i in range(len(x)):
73
+ if x[i]==False and w+len(x)-i<8192:
74
+ x[i]=True
75
+ w+=len(x)-i+1
76
+ p=[t[3] if t[5]=="_" else t[3]+"|"+t[5] for i,t in enumerate(c)]
77
+ d=[t[7] if t[6]=="0" else "l-"+t[7] if int(t[0])<int(t[6]) else "r-"+t[7] for t in c]
78
+ ids,upos=[-1],["SYM|_"]
79
+ for i in range(len(x)):
80
+ if x[i]:
81
+ ids.append(i)
82
+ upos.append(p[i]+"|"+d[i] if c[i][6]=="0" else p[i]+"|_")
83
+ for j in range(i+1,len(x)):
84
+ ids.append(j)
85
+ upos.append(p[j]+"|"+d[j] if int(c[j][6])==i+1 else p[i]+"|"+d[i] if int(c[i][6])==j+1 else p[j]+"|_")
86
+ if w>8192 and i>0:
87
+ while w>8192 and upos[-1].endswith("|_"):
88
+ upos.pop(-1)
89
+ ids.pop(-1)
90
+ w-=1
91
+ ids.append(-1)
92
+ upos.append("SYM|_")
93
+ with torch.no_grad():
94
+ m=[]
95
+ for j in v:
96
+ if j==[]:
97
+ j=[self.tokenizer.unk_token_id]
98
+ m.append(self.embeddings[j,:].sum(axis=0))
99
+ m.append(self.embeddings[self.tokenizer.sep_token_id,:])
100
+ emb=torch.stack(m)
101
+ return{"inputs_embeds":emb[ids[:8192],:],"labels":[self.label2id[p] for p in upos[:8192]]}
102
+ from transformers import AutoTokenizer,AutoConfig,AutoModelForTokenClassification,DefaultDataCollator,TrainingArguments,Trainer
103
+ tkz=AutoTokenizer.from_pretrained(src)
104
+ trainDS=UDEmbedsDataset("train.conllu",tkz)
105
+ devDS=UDEmbedsDataset("dev.conllu",tkz)
106
+ testDS=UDEmbedsDataset("test.conllu",tkz)
107
+ lid=trainDS(devDS,testDS)
108
+ cfg=AutoConfig.from_pretrained(src,num_labels=len(lid),label2id=lid,id2label={i:l for l,i in lid.items()},ignore_mismatched_sizes=True,trust_remote_code=True)
109
+ mdl=AutoModelForTokenClassification.from_pretrained(src,config=cfg,ignore_mismatched_sizes=True,trust_remote_code=True)
110
+ trainDS.embeddings=mdl.get_input_embeddings().weight
111
+ arg=TrainingArguments(num_train_epochs=3,per_device_train_batch_size=1,dataloader_pin_memory=False,output_dir=tgt,overwrite_output_dir=True,save_total_limit=2,learning_rate=5e-05,warmup_ratio=0.1,save_safetensors=False)
112
+ trn=Trainer(args=arg,data_collator=DefaultDataCollator(),model=mdl,train_dataset=trainDS)
113
+ trn.train()
114
+ trn.save_model(tgt)
115
+ tkz.save_pretrained(tgt)
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:830c264f28fba9953e623b9f3dd35e58d30bd6469e297dfaf1d2220e037e9ce4
3
+ size 663202290
special_tokens_map.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|padding|>",
4
+ "<|endoftext|>",
5
+ "[UNK]",
6
+ "[CLS]",
7
+ "[SEP]",
8
+ "[PAD]",
9
+ "[MASK]"
10
+ ],
11
+ "cls_token": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "mask_token": {
19
+ "content": "[MASK]",
20
+ "lstrip": true,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "[PAD]",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "sep_token": {
33
+ "content": "[SEP]",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "unk_token": {
40
+ "content": "[UNK]",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ }
46
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,954 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|padding|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "4": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "5": {
44
+ "content": "|||EMAIL_ADDRESS|||",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "6": {
52
+ "content": "|||PHONE_NUMBER|||",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": "|||IP_ADDRESS|||",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": " ",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": " ",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": " ",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "additional_special_tokens": [
933
+ "<|padding|>",
934
+ "<|endoftext|>",
935
+ "[UNK]",
936
+ "[CLS]",
937
+ "[SEP]",
938
+ "[PAD]",
939
+ "[MASK]"
940
+ ],
941
+ "clean_up_tokenization_spaces": true,
942
+ "cls_token": "[CLS]",
943
+ "extra_special_tokens": {},
944
+ "mask_token": "[MASK]",
945
+ "model_input_names": [
946
+ "input_ids",
947
+ "attention_mask"
948
+ ],
949
+ "model_max_length": 1000000000000000019884624838656,
950
+ "pad_token": "[PAD]",
951
+ "sep_token": "[SEP]",
952
+ "tokenizer_class": "PreTrainedTokenizerFast",
953
+ "unk_token": "[UNK]"
954
+ }
ud.py ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import numpy
2
+ from transformers import TokenClassificationPipeline
3
+
4
+ class BellmanFordTokenClassificationPipeline(TokenClassificationPipeline):
5
+ def __init__(self,**kwargs):
6
+ super().__init__(**kwargs)
7
+ x=self.model.config.label2id
8
+ y=[k for k in x if k.find("|")<0 and not k.startswith("I-")]
9
+ self.transition=numpy.full((len(x),len(x)),-numpy.inf)
10
+ for k,v in x.items():
11
+ if k.find("|")<0:
12
+ for j in ["I-"+k[2:]] if k.startswith("B-") else [k]+y if k.startswith("I-") else y:
13
+ self.transition[v,x[j]]=0
14
+ def check_model_type(self,supported_models):
15
+ pass
16
+ def postprocess(self,model_outputs,**kwargs):
17
+ if "logits" not in model_outputs:
18
+ return self.postprocess(model_outputs[0],**kwargs)
19
+ return self.bellman_ford_token_classification(model_outputs,**kwargs)
20
+ def bellman_ford_token_classification(self,model_outputs,**kwargs):
21
+ m=model_outputs["logits"][0].numpy()
22
+ e=numpy.exp(m-numpy.max(m,axis=-1,keepdims=True))
23
+ z=e/e.sum(axis=-1,keepdims=True)
24
+ for i in range(m.shape[0]-1,0,-1):
25
+ m[i-1]+=numpy.max(m[i]+self.transition,axis=1)
26
+ k=[numpy.argmax(m[0]+self.transition[0])]
27
+ for i in range(1,m.shape[0]):
28
+ k.append(numpy.argmax(m[i]+self.transition[k[-1]]))
29
+ w=[{"entity":self.model.config.id2label[j],"start":s,"end":e,"score":z[i,j]} for i,((s,e),j) in enumerate(zip(model_outputs["offset_mapping"][0].tolist(),k)) if s<e]
30
+ if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]!="none":
31
+ for i,t in reversed(list(enumerate(w))):
32
+ p=t.pop("entity")
33
+ if p.startswith("I-"):
34
+ w[i-1]["score"]=min(w[i-1]["score"],t["score"])
35
+ w[i-1]["end"]=w.pop(i)["end"]
36
+ elif p.startswith("B-"):
37
+ t["entity_group"]=p[2:]
38
+ else:
39
+ t["entity_group"]=p
40
+ for t in w:
41
+ t["text"]=model_outputs["sentence"][t["start"]:t["end"]]
42
+ return w
43
+
44
+ class UniversalDependenciesPipeline(BellmanFordTokenClassificationPipeline):
45
+ def __init__(self,**kwargs):
46
+ kwargs["aggregation_strategy"]="simple"
47
+ super().__init__(**kwargs)
48
+ x=self.model.config.label2id
49
+ self.root=numpy.full((len(x)),-numpy.inf)
50
+ self.left_arc=numpy.full((len(x)),-numpy.inf)
51
+ self.right_arc=numpy.full((len(x)),-numpy.inf)
52
+ for k,v in x.items():
53
+ if k.endswith("|root"):
54
+ self.root[v]=0
55
+ elif k.find("|l-")>0:
56
+ self.left_arc[v]=0
57
+ elif k.find("|r-")>0:
58
+ self.right_arc[v]=0
59
+ def postprocess(self,model_outputs,**kwargs):
60
+ import torch
61
+ kwargs["aggregation_strategy"]="simple"
62
+ if "logits" not in model_outputs:
63
+ return self.postprocess(model_outputs[0],**kwargs)
64
+ w=self.bellman_ford_token_classification(model_outputs,**kwargs)
65
+ off=[(t["start"],t["end"]) for t in w]
66
+ for i,(s,e) in reversed(list(enumerate(off))):
67
+ if s<e:
68
+ d=w[i]["text"]
69
+ j=len(d)-len(d.lstrip())
70
+ if j>0:
71
+ d=d.lstrip()
72
+ off[i]=(off[i][0]+j,off[i][1])
73
+ j=len(d)-len(d.rstrip())
74
+ if j>0:
75
+ d=d.rstrip()
76
+ off[i]=(off[i][0],off[i][1]-j)
77
+ if d.strip()=="":
78
+ off.pop(i)
79
+ w.pop(i)
80
+ v=self.tokenizer([t["text"] for t in w],add_special_tokens=False)
81
+ x=[not t["entity_group"].endswith(".") for t in w]
82
+ if len(x)<127:
83
+ x=[True]*len(x)
84
+ else:
85
+ k=sum([len(x)-i+1 if b else 0 for i,b in enumerate(x)])+1
86
+ for i in numpy.argsort(numpy.array([t["score"] for t in w])):
87
+ if x[i]==False and k+len(x)-i<8192:
88
+ x[i]=True
89
+ k+=len(x)-i+1
90
+ ids=[-1]
91
+ for i in range(len(x)):
92
+ if x[i]:
93
+ ids.append(i)
94
+ for j in range(i+1,len(x)):
95
+ ids.append(j)
96
+ ids.append(-1)
97
+ with torch.no_grad():
98
+ e=self.model.get_input_embeddings().weight
99
+ m=[]
100
+ for j in v["input_ids"]:
101
+ if j==[]:
102
+ j=[self.tokenizer.unk_token_id]
103
+ m.append(e[j,:].sum(axis=0))
104
+ m.append(e[self.tokenizer.sep_token_id,:])
105
+ m=torch.stack(m).to(self.device)
106
+ e=self.model(inputs_embeds=torch.unsqueeze(m[ids,:],0))
107
+ m=e.logits[0].cpu().numpy()
108
+ e=numpy.full((len(x),len(x),m.shape[-1]),m.min())
109
+ k=1
110
+ for i in range(len(x)):
111
+ if x[i]:
112
+ e[i,i]=m[k]+self.root
113
+ k+=1
114
+ for j in range(1,len(x)-i):
115
+ e[i+j,i]=m[k]+self.left_arc
116
+ e[i,i+j]=m[k]+self.right_arc
117
+ k+=1
118
+ k+=1
119
+ m,p=numpy.max(e,axis=2),numpy.argmax(e,axis=2)
120
+ h=self.chu_liu_edmonds(m)
121
+ z=[i for i,j in enumerate(h) if i==j]
122
+ if len(z)>1:
123
+ k,h=z[numpy.argmax(m[z,z])],numpy.min(m)-numpy.max(m)
124
+ m[:,z]+=[[0 if j in z and (i!=j or i==k) else h for i in z] for j in range(m.shape[0])]
125
+ h=self.chu_liu_edmonds(m)
126
+ q=[self.model.config.id2label[p[j,i]].split("|") for i,j in enumerate(h)]
127
+ t=model_outputs["sentence"].replace("\n"," ")
128
+ u="# text = "+t+"\n"
129
+ for i,(s,e) in enumerate(off):
130
+ u+="\t".join([str(i+1),t[s:e],"_",q[i][0],"_","_" if len(q[i])<3 else "|".join(q[i][1:-1]),str(0 if h[i]==i else h[i]+1),"root" if q[i][-1]=="root" else q[i][-1][2:],"_","_" if i+1<len(off) and e<off[i+1][0] else "SpaceAfter=No"])+"\n"
131
+ return u+"\n"
132
+ def chu_liu_edmonds(self,matrix):
133
+ h=numpy.argmax(matrix,axis=0)
134
+ x=[-1 if i==j else j for i,j in enumerate(h)]
135
+ for b in [lambda x,i,j:-1 if i not in x else x[i],lambda x,i,j:-1 if j<0 else x[j]]:
136
+ y=[]
137
+ while x!=y:
138
+ y=list(x)
139
+ for i,j in enumerate(x):
140
+ x[i]=b(x,i,j)
141
+ if max(x)<0:
142
+ return h
143
+ y,x=[i for i,j in enumerate(x) if j==max(x)],[i for i,j in enumerate(x) if j<max(x)]
144
+ z=matrix-numpy.max(matrix,axis=0)
145
+ m=numpy.block([[z[x,:][:,x],numpy.max(z[x,:][:,y],axis=1).reshape(len(x),1)],[numpy.max(z[y,:][:,x],axis=0),numpy.max(z[y,y])]])
146
+ k=[j if i==len(x) else x[j] if j<len(x) else y[numpy.argmax(z[y,x[i]])] for i,j in enumerate(self.chu_liu_edmonds(m))]
147
+ h=[j if i in y else k[x.index(i)] for i,j in enumerate(h)]
148
+ i=y[numpy.argmax(z[x[k[-1]],y] if k[-1]<len(x) else z[y,y])]
149
+ h[i]=x[k[-1]] if k[-1]<len(x) else i
150
+ return h