mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 01:46:28 +03:00
Merge remote-tracking branch 'upstream/develop' into fix/corpus
This commit is contained in:
svlandeg
commit
c8c84f1ccd
|
|
@ -1,137 +0,0 @@
|
|||
[paths]
|
||||
train = ""
|
||||
dev = ""
|
||||
raw = null
|
||||
init_tok2vec = null
|
||||
|
||||
[system]
|
||||
seed = 0
|
||||
use_pytorch_for_gpu_memory = false
|
||||
|
||||
[corpora]
|
||||
|
||||
[corpora.train]
|
||||
@readers = "spacy.Corpus.v1"
|
||||
path = ${paths:train}
|
||||
gold_preproc = true
|
||||
max_length = 0
|
||||
limit = 0
|
||||
|
||||
[corpora.dev]
|
||||
@readers = "spacy.Corpus.v1"
|
||||
path = ${paths:dev}
|
||||
gold_preproc = ${corpora.train.gold_preproc}
|
||||
max_length = 0
|
||||
limit = 0
|
||||
|
||||
[training]
|
||||
seed = ${system:seed}
|
||||
dropout = 0.1
|
||||
init_tok2vec = ${paths:init_tok2vec}
|
||||
vectors = null
|
||||
accumulate_gradient = 1
|
||||
max_steps = 0
|
||||
max_epochs = 0
|
||||
patience = 10000
|
||||
eval_frequency = 200
|
||||
score_weights = {"dep_las": 0.4, "ents_f": 0.4, "tag_acc": 0.2}
|
||||
frozen_components = []
|
||||
dev_corpus = "corpora.dev"
|
||||
train_corpus = "corpora.train"
|
||||
|
||||
[training.batcher]
|
||||
@batchers = "spacy.batch_by_words.v1"
|
||||
discard_oversize = false
|
||||
tolerance = 0.2
|
||||
|
||||
[training.batcher.size]
|
||||
@schedules = "compounding.v1"
|
||||
start = 100
|
||||
stop = 1000
|
||||
compound = 1.001
|
||||
|
||||
[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 = 1e-8
|
||||
learn_rate = 0.001
|
||||
|
||||
[nlp]
|
||||
lang = "en"
|
||||
load_vocab_data = false
|
||||
pipeline = ["tok2vec", "ner", "tagger", "parser"]
|
||||
|
||||
[nlp.tokenizer]
|
||||
@tokenizers = "spacy.Tokenizer.v1"
|
||||
|
||||
[nlp.lemmatizer]
|
||||
@lemmatizers = "spacy.Lemmatizer.v1"
|
||||
|
||||
[components]
|
||||
|
||||
[components.tok2vec]
|
||||
factory = "tok2vec"
|
||||
|
||||
[components.ner]
|
||||
factory = "ner"
|
||||
learn_tokens = false
|
||||
min_action_freq = 1
|
||||
|
||||
[components.tagger]
|
||||
factory = "tagger"
|
||||
|
||||
[components.parser]
|
||||
factory = "parser"
|
||||
learn_tokens = false
|
||||
min_action_freq = 30
|
||||
|
||||
[components.tagger.model]
|
||||
@architectures = "spacy.Tagger.v1"
|
||||
|
||||
[components.tagger.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecListener.v1"
|
||||
width = ${components.tok2vec.model.encode:width}
|
||||
|
||||
[components.parser.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v1"
|
||||
nr_feature_tokens = 8
|
||||
hidden_width = 128
|
||||
maxout_pieces = 2
|
||||
use_upper = true
|
||||
|
||||
[components.parser.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecListener.v1"
|
||||
width = ${components.tok2vec.model.encode:width}
|
||||
|
||||
[components.ner.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v1"
|
||||
nr_feature_tokens = 3
|
||||
hidden_width = 128
|
||||
maxout_pieces = 2
|
||||
use_upper = true
|
||||
|
||||
[components.ner.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecListener.v1"
|
||||
width = ${components.tok2vec.model.encode:width}
|
||||
|
||||
[components.tok2vec.model]
|
||||
@architectures = "spacy.Tok2Vec.v1"
|
||||
|
||||
[components.tok2vec.model.embed]
|
||||
@architectures = "spacy.MultiHashEmbed.v1"
|
||||
width = ${components.tok2vec.model.encode:width}
|
||||
rows = 2000
|
||||
also_embed_subwords = true
|
||||
also_use_static_vectors = false
|
||||
|
||||
[components.tok2vec.model.encode]
|
||||
@architectures = "spacy.MaxoutWindowEncoder.v1"
|
||||
width = 96
|
||||
depth = 4
|
||||
window_size = 1
|
||||
maxout_pieces = 3
|
||||
|
|
@ -1,152 +0,0 @@
|
|||
# Training hyper-parameters and additional features.
|
||||
[training]
|
||||
# Whether to train on sequences with 'gold standard' sentence boundaries
|
||||
# and tokens. If you set this to true, take care to ensure your run-time
|
||||
# data is passed in sentence-by-sentence via some prior preprocessing.
|
||||
gold_preproc = false
|
||||
# Limitations on training document length or number of examples.
|
||||
max_length = 0
|
||||
limit = 0
|
||||
# Data augmentation
|
||||
orth_variant_level = 0.0
|
||||
dropout = 0.1
|
||||
# Controls early-stopping. 0 or -1 mean unlimited.
|
||||
patience = 1600
|
||||
max_epochs = 0
|
||||
max_steps = 20000
|
||||
eval_frequency = 400
|
||||
# Other settings
|
||||
seed = 0
|
||||
accumulate_gradient = 1
|
||||
use_pytorch_for_gpu_memory = false
|
||||
# Control how scores are printed and checkpoints are evaluated.
|
||||
scores = ["speed", "tags_acc", "uas", "las", "ents_f"]
|
||||
score_weights = {"las": 0.4, "ents_f": 0.4, "tags_acc": 0.2}
|
||||
# These settings are invalid for the transformer models.
|
||||
init_tok2vec = null
|
||||
discard_oversize = false
|
||||
omit_extra_lookups = false
|
||||
batch_by = "words"
|
||||
use_gpu = -1
|
||||
raw_text = null
|
||||
tag_map = null
|
||||
|
||||
[training.batch_size]
|
||||
@schedules = "compounding.v1"
|
||||
start = 1000
|
||||
stop = 1000
|
||||
compound = 1.001
|
||||
|
||||
[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 = 1e-8
|
||||
learn_rate = 0.001
|
||||
|
||||
[pretraining]
|
||||
max_epochs = 1000
|
||||
min_length = 5
|
||||
max_length = 500
|
||||
dropout = 0.2
|
||||
n_save_every = null
|
||||
batch_size = 3000
|
||||
seed = ${training:seed}
|
||||
use_pytorch_for_gpu_memory = ${training:use_pytorch_for_gpu_memory}
|
||||
tok2vec_model = "nlp.pipeline.tok2vec.model"
|
||||
|
||||
[pretraining.objective]
|
||||
type = "characters"
|
||||
n_characters = 4
|
||||
|
||||
[pretraining.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 = 1e-8
|
||||
learn_rate = 0.001
|
||||
|
||||
[nlp]
|
||||
lang = "en"
|
||||
vectors = null
|
||||
base_model = null
|
||||
|
||||
[nlp.pipeline]
|
||||
|
||||
[nlp.pipeline.tok2vec]
|
||||
factory = "tok2vec"
|
||||
|
||||
[nlp.pipeline.senter]
|
||||
factory = "senter"
|
||||
|
||||
[nlp.pipeline.ner]
|
||||
factory = "ner"
|
||||
learn_tokens = false
|
||||
min_action_freq = 1
|
||||
beam_width = 1
|
||||
beam_update_prob = 1.0
|
||||
|
||||
[nlp.pipeline.tagger]
|
||||
factory = "tagger"
|
||||
|
||||
[nlp.pipeline.parser]
|
||||
factory = "parser"
|
||||
learn_tokens = false
|
||||
min_action_freq = 1
|
||||
beam_width = 1
|
||||
beam_update_prob = 1.0
|
||||
|
||||
[nlp.pipeline.senter.model]
|
||||
@architectures = "spacy.Tagger.v1"
|
||||
|
||||
[nlp.pipeline.senter.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecTensors.v1"
|
||||
width = ${nlp.pipeline.tok2vec.model:width}
|
||||
|
||||
[nlp.pipeline.tagger.model]
|
||||
@architectures = "spacy.Tagger.v1"
|
||||
|
||||
[nlp.pipeline.tagger.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecTensors.v1"
|
||||
width = ${nlp.pipeline.tok2vec.model:width}
|
||||
|
||||
[nlp.pipeline.parser.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v1"
|
||||
nr_feature_tokens = 8
|
||||
hidden_width = 128
|
||||
maxout_pieces = 3
|
||||
use_upper = false
|
||||
|
||||
[nlp.pipeline.parser.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecTensors.v1"
|
||||
width = ${nlp.pipeline.tok2vec.model:width}
|
||||
|
||||
[nlp.pipeline.ner.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v1"
|
||||
nr_feature_tokens = 3
|
||||
hidden_width = 128
|
||||
maxout_pieces = 3
|
||||
use_upper = false
|
||||
|
||||
[nlp.pipeline.ner.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecTensors.v1"
|
||||
width = ${nlp.pipeline.tok2vec.model:width}
|
||||
|
||||
[nlp.pipeline.tok2vec.model]
|
||||
@architectures = "spacy.HashEmbedCNN.v1"
|
||||
pretrained_vectors = ${nlp:vectors}
|
||||
width = 256
|
||||
depth = 6
|
||||
window_size = 1
|
||||
embed_size = 10000
|
||||
maxout_pieces = 3
|
||||
subword_features = true
|
||||
dropout = null
|
||||
|
|
@ -1,73 +0,0 @@
|
|||
# Training hyper-parameters and additional features.
|
||||
[training]
|
||||
# Whether to train on sequences with 'gold standard' sentence boundaries
|
||||
# and tokens. If you set this to true, take care to ensure your run-time
|
||||
# data is passed in sentence-by-sentence via some prior preprocessing.
|
||||
gold_preproc = false
|
||||
# Limitations on training document length or number of examples.
|
||||
max_length = 3000
|
||||
limit = 0
|
||||
# Data augmentation
|
||||
orth_variant_level = 0.0
|
||||
dropout = 0.1
|
||||
# Controls early-stopping. 0 or -1 mean unlimited.
|
||||
patience = 100000
|
||||
max_epochs = 0
|
||||
max_steps = 0
|
||||
eval_frequency = 1000
|
||||
# Other settings
|
||||
seed = 0
|
||||
accumulate_gradient = 1
|
||||
use_pytorch_for_gpu_memory = false
|
||||
# Control how scores are printed and checkpoints are evaluated.
|
||||
scores = ["speed", "ents_p", "ents_r", "ents_f"]
|
||||
score_weights = {"ents_f": 1.0}
|
||||
# These settings are invalid for the transformer models.
|
||||
init_tok2vec = null
|
||||
discard_oversize = false
|
||||
omit_extra_lookups = false
|
||||
batch_by = "words"
|
||||
|
||||
[training.batch_size]
|
||||
@schedules = "compounding.v1"
|
||||
start = 100
|
||||
stop = 1000
|
||||
compound = 1.001
|
||||
|
||||
[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 = 1e-8
|
||||
learn_rate = 0.001
|
||||
|
||||
[nlp]
|
||||
lang = "en"
|
||||
vectors = null
|
||||
|
||||
[nlp.pipeline.ner]
|
||||
factory = "ner"
|
||||
learn_tokens = false
|
||||
min_action_freq = 1
|
||||
|
||||
[nlp.pipeline.ner.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v1"
|
||||
nr_feature_tokens = 3
|
||||
hidden_width = 64
|
||||
maxout_pieces = 2
|
||||
use_upper = true
|
||||
|
||||
[nlp.pipeline.ner.model.tok2vec]
|
||||
@architectures = "spacy.HashEmbedCNN.v1"
|
||||
pretrained_vectors = ${nlp:vectors}
|
||||
width = 96
|
||||
depth = 4
|
||||
window_size = 1
|
||||
embed_size = 2000
|
||||
maxout_pieces = 3
|
||||
subword_features = true
|
||||
dropout = ${training:dropout}
|
||||
|
|
@ -1,73 +0,0 @@
|
|||
[training]
|
||||
patience = 10000
|
||||
eval_frequency = 200
|
||||
dropout = 0.2
|
||||
init_tok2vec = null
|
||||
vectors = null
|
||||
max_epochs = 100
|
||||
orth_variant_level = 0.0
|
||||
gold_preproc = true
|
||||
max_length = 0
|
||||
use_gpu = 0
|
||||
scores = ["tags_acc", "uas", "las"]
|
||||
score_weights = {"las": 0.8, "tags_acc": 0.2}
|
||||
limit = 0
|
||||
seed = 0
|
||||
accumulate_gradient = 2
|
||||
discard_oversize = false
|
||||
|
||||
[training.batch_size]
|
||||
@schedules = "compounding.v1"
|
||||
start = 100
|
||||
stop = 1000
|
||||
compound = 1.001
|
||||
|
||||
[training.optimizer]
|
||||
@optimizers = "Adam.v1"
|
||||
learn_rate = 0.001
|
||||
beta1 = 0.9
|
||||
beta2 = 0.999
|
||||
|
||||
[nlp]
|
||||
lang = "en"
|
||||
vectors = ${training:vectors}
|
||||
|
||||
[nlp.pipeline.tok2vec]
|
||||
factory = "tok2vec"
|
||||
|
||||
[nlp.pipeline.tagger]
|
||||
factory = "tagger"
|
||||
|
||||
[nlp.pipeline.parser]
|
||||
factory = "parser"
|
||||
learn_tokens = false
|
||||
min_action_freq = 1
|
||||
beam_width = 1
|
||||
beam_update_prob = 1.0
|
||||
|
||||
[nlp.pipeline.tagger.model]
|
||||
@architectures = "spacy.Tagger.v1"
|
||||
|
||||
[nlp.pipeline.tagger.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecTensors.v1"
|
||||
width = ${nlp.pipeline.tok2vec.model:width}
|
||||
|
||||
[nlp.pipeline.parser.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v1"
|
||||
nr_feature_tokens = 8
|
||||
hidden_width = 64
|
||||
maxout_pieces = 3
|
||||
|
||||
[nlp.pipeline.parser.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecTensors.v1"
|
||||
width = ${nlp.pipeline.tok2vec.model:width}
|
||||
|
||||
[nlp.pipeline.tok2vec.model]
|
||||
@architectures = "spacy.HashEmbedBiLSTM.v1"
|
||||
pretrained_vectors = ${nlp:vectors}
|
||||
width = 96
|
||||
depth = 4
|
||||
embed_size = 2000
|
||||
subword_features = true
|
||||
maxout_pieces = 3
|
||||
dropout = null
|
||||
|
|
@ -1,112 +0,0 @@
|
|||
[paths]
|
||||
train = ""
|
||||
dev = ""
|
||||
raw = null
|
||||
init_tok2vec = null
|
||||
|
||||
[system]
|
||||
seed = 0
|
||||
use_pytorch_for_gpu_memory = false
|
||||
|
||||
[corpora]
|
||||
|
||||
[corpora.train]
|
||||
@readers = "spacy.Corpus.v1"
|
||||
path = ${paths:train}
|
||||
gold_preproc = true
|
||||
max_length = 0
|
||||
limit = 0
|
||||
|
||||
[corpora.dev]
|
||||
@readers = "spacy.Corpus.v1"
|
||||
path = ${paths:dev}
|
||||
gold_preproc = ${corpora.train.gold_preproc}
|
||||
max_length = 0
|
||||
limit = 0
|
||||
|
||||
[training]
|
||||
seed = ${system:seed}
|
||||
dropout = 0.2
|
||||
init_tok2vec = ${paths:init_tok2vec}
|
||||
vectors = null
|
||||
accumulate_gradient = 1
|
||||
max_steps = 0
|
||||
max_epochs = 0
|
||||
patience = 10000
|
||||
eval_frequency = 200
|
||||
score_weights = {"dep_las": 0.8, "tag_acc": 0.2}
|
||||
|
||||
[training.batcher]
|
||||
@batchers = "spacy.batch_by_words.v1"
|
||||
discard_oversize = false
|
||||
tolerance = 0.2
|
||||
|
||||
[training.batcher.size]
|
||||
@schedules = "compounding.v1"
|
||||
start = 100
|
||||
stop = 1000
|
||||
compound = 1.001
|
||||
|
||||
[training.optimizer]
|
||||
@optimizers = "Adam.v1"
|
||||
learn_rate = 0.001
|
||||
beta1 = 0.9
|
||||
beta2 = 0.999
|
||||
|
||||
[nlp]
|
||||
lang = "en"
|
||||
pipeline = ["tok2vec", "tagger", "parser"]
|
||||
load_vocab_data = false
|
||||
|
||||
[nlp.tokenizer]
|
||||
@tokenizers = "spacy.Tokenizer.v1"
|
||||
|
||||
[nlp.lemmatizer]
|
||||
@lemmatizers = "spacy.Lemmatizer.v1"
|
||||
|
||||
[components]
|
||||
|
||||
[components.tok2vec]
|
||||
factory = "tok2vec"
|
||||
|
||||
[components.tagger]
|
||||
factory = "tagger"
|
||||
|
||||
[components.parser]
|
||||
factory = "parser"
|
||||
learn_tokens = false
|
||||
min_action_freq = 1
|
||||
|
||||
[components.tagger.model]
|
||||
@architectures = "spacy.Tagger.v1"
|
||||
|
||||
[components.tagger.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecListener.v1"
|
||||
width = ${components.tok2vec.model.encode:width}
|
||||
|
||||
[components.parser.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v1"
|
||||
nr_feature_tokens = 8
|
||||
hidden_width = 64
|
||||
maxout_pieces = 3
|
||||
|
||||
[components.parser.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecListener.v1"
|
||||
width = ${components.tok2vec.model.encode:width}
|
||||
|
||||
[components.tok2vec.model]
|
||||
@architectures = "spacy.Tok2Vec.v1"
|
||||
|
||||
[components.tok2vec.model.embed]
|
||||
@architectures = "spacy.MultiHashEmbed.v1"
|
||||
width = ${components.tok2vec.model.encode:width}
|
||||
rows = 2000
|
||||
also_embed_subwords = true
|
||||
also_use_static_vectors = false
|
||||
|
||||
[components.tok2vec.model.encode]
|
||||
@architectures = "spacy.MaxoutWindowEncoder.v1"
|
||||
width = 96
|
||||
depth = 4
|
||||
window_size = 1
|
||||
maxout_pieces = 3
|
||||
|
|
@ -1,69 +0,0 @@
|
|||
[training]
|
||||
use_gpu = -1
|
||||
limit = 0
|
||||
dropout = 0.2
|
||||
patience = 10000
|
||||
eval_frequency = 200
|
||||
scores = ["ents_f"]
|
||||
score_weights = {"ents_f": 1}
|
||||
orth_variant_level = 0.0
|
||||
gold_preproc = true
|
||||
max_length = 0
|
||||
batch_size = 25
|
||||
seed = 0
|
||||
accumulate_gradient = 2
|
||||
discard_oversize = false
|
||||
|
||||
[training.optimizer]
|
||||
@optimizers = "Adam.v1"
|
||||
learn_rate = 0.001
|
||||
beta1 = 0.9
|
||||
beta2 = 0.999
|
||||
|
||||
[nlp]
|
||||
lang = "en"
|
||||
vectors = null
|
||||
|
||||
[nlp.pipeline.tok2vec]
|
||||
factory = "tok2vec"
|
||||
|
||||
[nlp.pipeline.tok2vec.model]
|
||||
@architectures = "spacy.Tok2Vec.v1"
|
||||
|
||||
[nlp.pipeline.tok2vec.model.extract]
|
||||
@architectures = "spacy.CharacterEmbed.v1"
|
||||
width = 96
|
||||
nM = 64
|
||||
nC = 8
|
||||
rows = 2000
|
||||
columns = ["ID", "NORM", "PREFIX", "SUFFIX", "SHAPE", "ORTH"]
|
||||
dropout = null
|
||||
|
||||
[nlp.pipeline.tok2vec.model.extract.features]
|
||||
@architectures = "spacy.Doc2Feats.v1"
|
||||
columns = ${nlp.pipeline.tok2vec.model.extract:columns}
|
||||
|
||||
[nlp.pipeline.tok2vec.model.embed]
|
||||
@architectures = "spacy.LayerNormalizedMaxout.v1"
|
||||
width = ${nlp.pipeline.tok2vec.model.extract:width}
|
||||
maxout_pieces = 4
|
||||
|
||||
[nlp.pipeline.tok2vec.model.encode]
|
||||
@architectures = "spacy.MaxoutWindowEncoder.v1"
|
||||
width = ${nlp.pipeline.tok2vec.model.extract:width}
|
||||
window_size = 1
|
||||
maxout_pieces = 2
|
||||
depth = 2
|
||||
|
||||
[nlp.pipeline.ner]
|
||||
factory = "ner"
|
||||
|
||||
[nlp.pipeline.ner.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v1"
|
||||
nr_feature_tokens = 6
|
||||
hidden_width = 64
|
||||
maxout_pieces = 2
|
||||
|
||||
[nlp.pipeline.ner.model.tok2vec]
|
||||
@architectures = "spacy.Tok2VecTensors.v1"
|
||||
width = ${nlp.pipeline.tok2vec.model.extract:width}
|
||||
|
|
@ -1,51 +0,0 @@
|
|||
[training]
|
||||
use_gpu = -1
|
||||
limit = 0
|
||||
dropout = 0.2
|
||||
patience = 10000
|
||||
eval_frequency = 200
|
||||
scores = ["ents_p", "ents_r", "ents_f"]
|
||||
score_weights = {"ents_f": 1}
|
||||
orth_variant_level = 0.0
|
||||
gold_preproc = true
|
||||
max_length = 0
|
||||
seed = 0
|
||||
accumulate_gradient = 2
|
||||
discard_oversize = false
|
||||
|
||||
[training.batch_size]
|
||||
@schedules = "compounding.v1"
|
||||
start = 3000
|
||||
stop = 3000
|
||||
compound = 1.001
|
||||
|
||||
|
||||
[training.optimizer]
|
||||
@optimizers = "Adam.v1"
|
||||
learn_rate = 0.001
|
||||
beta1 = 0.9
|
||||
beta2 = 0.999
|
||||
|
||||
[nlp]
|
||||
lang = "en"
|
||||
vectors = null
|
||||
|
||||
[nlp.pipeline.ner]
|
||||
factory = "ner"
|
||||
|
||||
[nlp.pipeline.ner.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v1"
|
||||
nr_feature_tokens = 6
|
||||
hidden_width = 64
|
||||
maxout_pieces = 2
|
||||
|
||||
[nlp.pipeline.ner.model.tok2vec]
|
||||
@architectures = "spacy.HashEmbedCNN.v1"
|
||||
width = 128
|
||||
depth = 4
|
||||
embed_size = 7000
|
||||
maxout_pieces = 3
|
||||
window_size = 1
|
||||
subword_features = true
|
||||
pretrained_vectors = null
|
||||
dropout = null
|
||||
|
|
@ -710,6 +710,48 @@ nlp = spacy.blank("en")
|
|||
+ nlp.add_pipe("ner", source=source_nlp)
|
||||
```
|
||||
|
||||
#### Configuring pipeline components with settings {#migrating-configure-pipe}
|
||||
|
||||
Because pipeline components are now added using their string names, you won't
|
||||
have to instantiate the [component classes](/api/#architecture-pipeline)
|
||||
directly anynore. To configure the component, you can now use the `config`
|
||||
argument on [`nlp.add_pipe`](/api/language#add_pipe).
|
||||
|
||||
> #### config.cfg (excerpt)
|
||||
>
|
||||
> ```ini
|
||||
> [components.sentencizer]
|
||||
> factory = "sentencizer"
|
||||
> punct_chars = ["!", ".", "?"]
|
||||
> ```
|
||||
|
||||
```diff
|
||||
punct_chars = ["!", ".", "?"]
|
||||
- sentencizer = Sentencizer(punct_chars=punct_chars)
|
||||
+ sentencizer = nlp.add_pipe("sentencizer", config={"punct_chars": punct_chars})
|
||||
```
|
||||
|
||||
The `config` corresponds to the component settings in the
|
||||
[`config.cfg`](/usage/training#config-components) and will overwrite the default
|
||||
config defined by the components.
|
||||
|
||||
<Infobox variant="warning" title="Important note on config values">
|
||||
|
||||
Config values you pass to components **need to be JSON-serializable** and can't
|
||||
be arbitrary Python objects. Otherwise, the settings you provide can't be
|
||||
represented in the `config.cfg` and spaCy has no way of knowing how to re-create
|
||||
your component with the same settings when you load the pipeline back in. If you
|
||||
need to pass arbitrary objects to a component, use a
|
||||
[registered function](/usage/processing-pipelines#example-stateful-components):
|
||||
|
||||
```diff
|
||||
- config = {"model": MyTaggerModel()}
|
||||
+ config= {"model": {"@architectures": "MyTaggerModel"}}
|
||||
tagger = nlp.add_pipe("tagger", config=config)
|
||||
```
|
||||
|
||||
</Infobox>
|
||||
|
||||
### Adding match patterns {#migrating-matcher}
|
||||
|
||||
The [`Matcher.add`](/api/matcher#add),
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user