mk_core_news_md / config.cfg
adrianeboyd's picture
Update spaCy pipeline
470f9da
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null
[system]
gpu_allocator = null
seed = 0
[nlp]
lang = "mk"
pipeline = ["morphologizer","parser","senter","attribute_ruler","lemmatizer","ner"]
disabled = ["senter"]
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 256
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
vectors = {"@vectors":"spacy.Vectors.v1"}
[components]
[components.attribute_ruler]
factory = "attribute_ruler"
scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"}
validate = false
[components.lemmatizer]
factory = "lemmatizer"
mode = "rule"
model = null
overwrite = false
scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
[components.morphologizer]
factory = "morphologizer"
extend = false
label_smoothing = 0.0
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.Tok2Vec.v2"
[components.morphologizer.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = ${components.morphologizer.model.tok2vec.encode:width}
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
rows = [5000,1000,2500,2500,50,50]
include_static_vectors = true
[components.morphologizer.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[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 = true
nO = null
[components.ner.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"
[components.ner.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 96
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,1000,2500,2500]
include_static_vectors = true
[components.ner.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[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 = 64
maxout_pieces = 2
use_upper = true
nO = null
[components.parser.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"
[components.parser.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 96
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
rows = [5000,1000,2500,2500,50,50]
include_static_vectors = true
[components.parser.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[components.senter]
factory = "senter"
overwrite = false
scorer = {"@scorers":"spacy.senter_scorer.v1"}
[components.senter.model]
@architectures = "spacy.Tagger.v2"
nO = null
normalize = false
[components.senter.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"
[components.senter.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 16
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
rows = [1000,500,500,500,50]
include_static_vectors = true
[components.senter.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 16
depth = 2
window_size = 1
maxout_pieces = 2
[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]
train_corpus = "corpora.train"
dev_corpus = "corpora.dev"
seed = ${system:seed}
gpu_allocator = ${system:gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 5000
max_epochs = 0
max_steps = 100000
eval_frequency = 1000
frozen_components = []
before_to_disk = null
annotating_components = []
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 = true
eps = 0.00000001
learn_rate = 0.001
[training.score_weights]
pos_acc = 0.16
morph_acc = null
morph_per_feat = null
dep_uas = 0.0
dep_las = 0.16
dep_las_per_type = null
sents_p = 0.0
sents_r = 0.0
sents_f = 0.02
lemma_acc = 0.5
ents_f = 0.16
ents_p = 0.0
ents_r = 0.0
ents_per_type = null
speed = 0.0
[pretraining]
[initialize]
vocab_data = null
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
before_init = null
after_init = null
[initialize.components]
[initialize.components.morphologizer]
[initialize.components.morphologizer.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/morphologizer.json"
require = false
[initialize.components.ner]
[initialize.components.ner.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/ner.json"
require = false
[initialize.components.parser]
[initialize.components.parser.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/parser.json"
require = false
[initialize.lookups]
@misc = "spacy.LookupsDataLoader.v1"
lang = ${nlp.lang}
tables = ["lexeme_norm"]
[initialize.tokenizer]