config.cfg

[paths]
train = "02_train"
dev = "03_valid"
vectors = null
init_tok2vec = null

[system]
gpu_allocator = null
seed = 0

[nlp]
lang = "sr"
pipeline = ["tok2vec","tagger","ner","sentencizer","entity_linker"]
batch_size = 1000
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}

[components]

[components.entity_linker]
factory = "entity_linker"
candidates_batch_size = 1
entity_vector_length = 64
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 = false
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.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 = true
hidden_width = 300
maxout_pieces = 2
use_upper = true
nO = null

[components.ner.model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v2"
pretrained_vectors = null
width = 300
depth = 8
embed_size = 10000
window_size = 1
maxout_pieces = 3
subword_features = true

[components.sentencizer]
factory = "sentencizer"
overwrite = false
punct_chars = null
scorer = {"@scorers":"spacy.senter_scorer.v1"}

[components.tagger]
factory = "tagger"
label_smoothing = 0.0
neg_prefix = "!"
overwrite = false
scorer = {"@scorers":"spacy.tagger_scorer.v1"}

[components.tagger.model]
@architectures = "spacy.Tagger.v1"
nO = null

[components.tagger.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = 300
upstream = "*"

[components.tok2vec]
factory = "tok2vec"

[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"

[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 300
attrs = ["ORTH","SHAPE"]
rows = [5000,2500]
include_static_vectors = true

[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 300
depth = 4
window_size = 1
maxout_pieces = 3

[corpora]

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

[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
max_length = 2000
gold_preproc = false
limit = 0
augmenter = null

[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
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 = []
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 = 0.17
ents_f = 0.17
ents_p = 0.0
ents_r = 0.0
ents_per_type = null
sents_f = 0.33
sents_p = 0.0
sents_r = 0.0
nel_micro_f = 0.33
nel_micro_r = null
nel_micro_p = null

[pretraining]

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

[initialize.components]

[initialize.tokenizer]