en_ner_jnlpba_md / config.cfg
daviibrt's picture
Update spaCy pipeline
c8444e5 verified
[paths]
vectors = "output/en_core_sci_md_vectors"
init_tok2vec = null
parser_tagger_path = "output/en_core_sci_md_parser_tagger/model-best"
dev_path = "assets/JNLPBA-IOB/devel.tsv"
train_path = "assets/JNLPBA-IOB/train.tsv"
vocab_path = "project_data/vocab_md.jsonl"
train = null
dev = null
[system]
gpu_allocator = null
seed = 0
[nlp]
lang = "en"
pipeline = ["tok2vec","tagger","attribute_ruler","lemmatizer","parser","ner"]
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 1000
[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.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 = 128
maxout_pieces = 3
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","SPACY"]
rows = [5000,2500,2500,2500,100]
include_static_vectors = ${vars.include_static_vectors}
[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 = 128
maxout_pieces = 3
use_upper = true
nO = null
[components.parser.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = 96
upstream = "*"
[components.tagger]
factory = "tagger"
label_smoothing = 0.0
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.Tok2VecListener.v1"
width = 96
upstream = "*"
[components.tok2vec]
factory = "tok2vec"
[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"
[components.tok2vec.model.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.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[corpora]
[corpora.dev]
@readers = "specialized_ner_reader"
file_path = ${paths.dev_path}
[corpora.train]
@readers = "specialized_ner_reader"
file_path = ${paths.train_path}
[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 0
max_epochs = 7
max_steps = 0
eval_frequency = 500
frozen_components = ["tok2vec","parser","tagger","attribute_ruler","lemmatizer"]
before_to_disk = null
annotating_components = []
before_update = null
[training.batcher]
@batchers = "spacy.batch_by_sequence.v1"
get_length = null
[training.batcher.size]
@schedules = "compounding.v1"
start = 1
stop = 32
compound = 1.001
t = 0.0
[training.logger]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = true
[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 = null
lemma_acc = 0.5
dep_uas = null
dep_las = null
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = null
ents_f = 0.5
ents_p = 0.0
ents_r = 0.0
ents_per_type = null
[pretraining]
[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = ${paths.vocab_path}
lookups = null
before_init = {"@callbacks":"replace_tokenizer"}
after_init = null
[initialize.components]
[initialize.tokenizer]
[vars]
include_static_vectors = "True"