en_statistics / config.cfg
etikaj-digital
Update spaCy pipeline
5af7e49
raw history blame
No virus
4.82 kB
[paths]
train = "corpus/en-core-web/train.spacy"
dev = "corpus/en-core-web/dev.spacy"
vectors = "corpus/en_vectors"
raw = null
init_tok2vec = null
vocab_data = null
[system]
gpu_allocator = null
seed = 0
[nlp]
lang = "en"
pipeline = ["tok2vec","tagger","parser","senter","attribute_ruler","lemmatizer","syllables","formality","readability"]
disabled = ["senter"]
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 256
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.attribute_ruler]
factory = "attribute_ruler"
validate = false
[components.formality]
factory = "formality"
[components.lemmatizer]
factory = "lemmatizer"
mode = "rule"
model = null
overwrite = false
[components.parser]
factory = "parser"
learn_tokens = false
min_action_freq = 30
moves = null
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.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode:width}
upstream = "tok2vec"
[components.readability]
factory = "readability"
[components.senter]
factory = "senter"
[components.senter.model]
@architectures = "spacy.Tagger.v1"
nO = null
[components.senter.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"
[components.senter.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 16
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [1000,500,500,500]
include_static_vectors = true
[components.senter.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 16
depth = 2
window_size = 1
maxout_pieces = 2
[components.syllables]
factory = "syllables"
[components.tagger]
factory = "tagger"
[components.tagger.model]
@architectures = "spacy.Tagger.v1"
nO = null
[components.tagger.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode:width}
upstream = "tok2vec"
[components.tok2vec]
factory = "tok2vec"
[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"
[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = ${components.tok2vec.model.encode:width}
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,2500,2500,2500]
include_static_vectors = true
[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[corpora]
[corpora.dev]
@readers = "spacy.Corpus.v1"
limit = 0
max_length = 0
path = ${paths:dev}
gold_preproc = false
augmenter = null
[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths:train}
max_length = 5000
gold_preproc = false
limit = 0
[corpora.train.augmenter]
@augmenters = "spacy.orth_variants.v1"
level = 0.2
lower = 0.5
[corpora.train.augmenter.orth_variants]
@readers = "srsly.read_json.v1"
path = "assets/orth_variants.json"
[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 = 0
eval_frequency = 1000
frozen_components = []
before_to_disk = null
annotating_components = []
[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.WandbLogger.v1"
project_name = "spacy-v3.0.0a2"
remove_config_values = []
[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]
tag_acc = 0.16
dep_uas = 0.0
dep_las = 0.16
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = 0.02
lemma_acc = 0.33
ents_f = 0.33
ents_p = 0.0
ents_r = 0.0
ents_per_type = null
[pretraining]
[initialize]
vocab_data = ${paths.vocab_data}
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
before_init = null
after_init = null
[initialize.components]
[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.components.tagger]
[initialize.components.tagger.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/tagger.json"
require = false
[initialize.lookups]
@misc = "spacy.LookupsDataLoader.v1"
lang = ${nlp.lang}
tables = ["lexeme_norm"]
[initialize.tokenizer]