File size: 7,269 Bytes
91c9fac
aed2231
 
91c9fac
aed2231
 
91c9fac
 
 
aed2231
91c9fac
 
 
aed2231
 
91c9fac
 
 
 
 
 
 
 
aed2231
 
 
91c9fac
aed2231
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91c9fac
 
 
aed2231
 
 
91c9fac
 
aed2231
91c9fac
aed2231
91c9fac
 
 
 
 
aed2231
91c9fac
 
 
 
 
aed2231
91c9fac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aed2231
91c9fac
 
 
 
 
 
aed2231
91c9fac
 
 
 
 
 
aed2231
 
91c9fac
 
 
 
 
 
aed2231
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91c9fac
 
 
aed2231
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91c9fac
 
 
 
 
 
aed2231
 
 
91c9fac
 
 
aed2231
 
 
 
91c9fac
 
 
aed2231
 
91c9fac
 
 
 
 
aed2231
91c9fac
aed2231
 
91c9fac
 
 
 
aed2231
91c9fac
aed2231
91c9fac
aed2231
91c9fac
 
aed2231
 
91c9fac
aed2231
 
91c9fac
 
aed2231
91c9fac
 
aed2231
 
 
 
91c9fac
 
aed2231
 
 
91c9fac
aed2231
 
 
 
 
 
 
91c9fac
 
aed2231
 
91c9fac
 
 
 
 
 
 
 
aed2231
91c9fac
aed2231
91c9fac
 
aed2231
 
 
91c9fac
aed2231
 
 
91c9fac
 
 
aed2231
 
91c9fac
 
 
aed2231
 
 
 
 
 
 
91c9fac
 
 
 
 
 
aed2231
 
91c9fac
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
[paths]
train = null
dev = null
init_tok2vec = null
vectors = null
model_source = "training/da_dacy_medium_trf/model-last"

[system]
gpu_allocator = "pytorch"
seed = 0

[nlp]
lang = "da"
pipeline = ["transformer","tagger","morphologizer","trainable_lemmatizer","parser","ner","coref","span_resolver","span_cleaner","entity_linker"]
batch_size = 512
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}

[components]

[components.coref]
factory = "experimental_coref"
span_cluster_prefix = "coref_head_clusters"

[components.coref.model]
@architectures = "spacy-experimental.Coref.v1"
distance_embedding_size = 20
dropout = 0.3
hidden_size = 1024
depth = 2
antecedent_limit = 100
antecedent_batch_size = 512

[components.coref.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 0.5
upstream = "transformer"
pooling = {"@layers":"reduce_mean.v1"}

[components.coref.scorer]
@scorers = "spacy-experimental.coref_scorer.v1"
span_cluster_prefix = "coref_head_clusters"

[components.entity_linker]
factory = "entity_linker"
candidates_batch_size = 1
entity_vector_length = 768
generate_empty_kb = {"@misc":"spacy.EmptyKB.v2"}
get_candidates = {"@misc":"spacy.CandidateGenerator.v1"}
get_candidates_batch = {"@misc":"spacy.CandidateBatchGenerator.v1"}
incl_context = true
incl_prior = true
labels_discard = []
n_sents = 0
overwrite = true
scorer = {"@scorers":"spacy.entity_linker_scorer.v1"}
threshold = null
use_gold_ents = true

[components.entity_linker.model]
@architectures = "spacy.EntityLinker.v2"
nO = null

[components.entity_linker.model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v2"
pretrained_vectors = null
width = 96
depth = 2
embed_size = 2000
window_size = 1
maxout_pieces = 3
subword_features = true

[components.morphologizer]
factory = "morphologizer"
extend = false
overwrite = true
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}

[components.morphologizer.model]
@architectures = "spacy.Tagger.v2"
nO = null
normalize = false

[components.morphologizer.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "transformer"

[components.ner]
factory = "ner"
incorrect_spans_key = null
moves = null
scorer = {"@scorers":"spacy.ner_scorer.v1"}
update_with_oracle_cut_size = 100

[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = false
nO = null

[components.ner.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "transformer"

[components.parser]
factory = "parser"
learn_tokens = false
min_action_freq = 30
moves = null
scorer = {"@scorers":"spacy.parser_scorer.v1"}
update_with_oracle_cut_size = 100

[components.parser.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "parser"
extra_state_tokens = false
hidden_width = 128
maxout_pieces = 3
use_upper = false
nO = null

[components.parser.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "transformer"

[components.span_cleaner]
factory = "experimental_span_cleaner"
prefix = "coref_head_clusters"

[components.span_resolver]
factory = "experimental_span_resolver"
input_prefix = "coref_head_clusters"
output_prefix = "coref_clusters"

[components.span_resolver.model]
@architectures = "spacy-experimental.SpanResolver.v1"
hidden_size = 1024
distance_embedding_size = 64
conv_channels = 4
window_size = 1
max_distance = 128
prefix = "coref_head_clusters"

[components.span_resolver.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 0.0
upstream = "transformer"
pooling = {"@layers":"reduce_mean.v1"}

[components.span_resolver.scorer]
@scorers = "spacy-experimental.span_resolver_scorer.v1"
input_prefix = "coref_head_clusters"
output_prefix = "coref_clusters"

[components.tagger]
factory = "tagger"
neg_prefix = "!"
overwrite = false
scorer = {"@scorers":"spacy.tagger_scorer.v1"}

[components.tagger.model]
@architectures = "spacy.Tagger.v2"
nO = null
normalize = false

[components.tagger.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "transformer"

[components.trainable_lemmatizer]
factory = "trainable_lemmatizer"
backoff = "orth"
min_tree_freq = 3
overwrite = false
scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
top_k = 1

[components.trainable_lemmatizer.model]
@architectures = "spacy.Tagger.v2"
nO = null
normalize = false

[components.trainable_lemmatizer.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "transformer"

[components.transformer]
factory = "transformer"
max_batch_items = 4096
set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}

[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v3"
name = "vesteinn/DanskBERT"
mixed_precision = false

[components.transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 400
stride = 350

[components.transformer.model.grad_scaler_config]

[components.transformer.model.tokenizer_config]
use_fast = true

[components.transformer.model.transformer_config]

[corpora]

[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
gold_preproc = false
max_length = 0
limit = 0
augmenter = null

[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
gold_preproc = false
max_length = 0
limit = 0
augmenter = null

[training]
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 200
frozen_components = []
annotating_components = []
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
before_to_disk = null
before_update = null

[training.batcher]
@batchers = "spacy.batch_by_words.v1"
discard_oversize = false
tolerance = 0.2
get_length = null

[training.batcher.size]
@schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001
t = 0.0

[training.logger]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = false

[training.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.999
L2_is_weight_decay = true
L2 = 0.01
grad_clip = 1.0
use_averages = false
eps = 0.00000001
learn_rate = 0.001

[training.score_weights]
tag_acc = 0.12
pos_acc = 0.06
morph_acc = 0.06
morph_per_feat = null
lemma_acc = 0.12
dep_uas = 0.06
dep_las = 0.06
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = 0.0
ents_f = 0.12
ents_p = 0.0
ents_r = 0.0
ents_per_type = null
coref_f = 0.12
coref_p = null
coref_r = null
span_accuracy = 0.12
nel_micro_f = 0.12
nel_micro_r = null
nel_micro_p = null

[pretraining]

[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null

[initialize.components]

[initialize.tokenizer]