|
[paths] |
|
train = "corpus/dane/train.spacy" |
|
dev = "corpus/dane/dev.spacy" |
|
vectors = null |
|
raw = null |
|
init_tok2vec = null |
|
vocab_data = null |
|
|
|
[system] |
|
gpu_allocator = "pytorch" |
|
seed = 1 |
|
|
|
[nlp] |
|
lang = "da" |
|
pipeline = ["transformer","morphologizer","parser","attribute_ruler","lemmatizer","ner"] |
|
disabled = [] |
|
before_creation = null |
|
after_creation = null |
|
after_pipeline_creation = null |
|
batch_size = 64 |
|
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} |
|
|
|
[components] |
|
|
|
[components.attribute_ruler] |
|
factory = "attribute_ruler" |
|
validate = false |
|
|
|
[components.lemmatizer] |
|
factory = "lemmatizer" |
|
mode = "lookup" |
|
model = null |
|
overwrite = false |
|
|
|
[components.morphologizer] |
|
factory = "morphologizer" |
|
|
|
[components.morphologizer.model] |
|
@architectures = "spacy.Tagger.v1" |
|
nO = null |
|
|
|
[components.morphologizer.model.tok2vec] |
|
@architectures = "spacy-transformers.TransformerListener.v1" |
|
grad_factor = 1.0 |
|
upstream = "transformer" |
|
pooling = {"@layers":"reduce_mean.v1"} |
|
|
|
[components.ner] |
|
factory = "ner" |
|
incorrect_spans_key = null |
|
moves = null |
|
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 = false |
|
nO = null |
|
|
|
[components.ner.model.tok2vec] |
|
@architectures = "spacy-transformers.TransformerListener.v1" |
|
grad_factor = 1.0 |
|
upstream = "transformer" |
|
pooling = {"@layers":"reduce_mean.v1"} |
|
|
|
[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 = false |
|
nO = null |
|
|
|
[components.parser.model.tok2vec] |
|
@architectures = "spacy-transformers.TransformerListener.v1" |
|
grad_factor = 1.0 |
|
upstream = "transformer" |
|
pooling = {"@layers":"reduce_mean.v1"} |
|
|
|
[components.transformer] |
|
factory = "transformer" |
|
max_batch_items = 4096 |
|
set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"} |
|
|
|
[components.transformer.model] |
|
@architectures = "spacy-transformers.TransformerModel.v1" |
|
name = "Maltehb/-l-ctra-danish-electra-small-cased" |
|
|
|
[components.transformer.model.get_spans] |
|
@span_getters = "spacy-transformers.strided_spans.v1" |
|
window = 128 |
|
stride = 96 |
|
|
|
[components.transformer.model.tokenizer_config] |
|
use_fast = true |
|
strip_accents = false |
|
|
|
[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 = 500 |
|
gold_preproc = false |
|
limit = 0 |
|
|
|
[corpora.train.augmenter] |
|
@augmenters = "spacy.lower_case.v1" |
|
level = 0.1 |
|
|
|
[training] |
|
train_corpus = "corpora.train" |
|
dev_corpus = "corpora.dev" |
|
seed = ${system:seed} |
|
gpu_allocator = ${system:gpu_allocator} |
|
dropout = 0.1 |
|
accumulate_gradient = 3 |
|
patience = 5000 |
|
max_epochs = 0 |
|
max_steps = 1 |
|
eval_frequency = 1000 |
|
frozen_components = [] |
|
before_to_disk = null |
|
annotating_components = [] |
|
|
|
[training.batcher] |
|
@batchers = "spacy.batch_by_padded.v1" |
|
discard_oversize = true |
|
get_length = null |
|
size = 2000 |
|
buffer = 256 |
|
|
|
[training.logger] |
|
@loggers = "spacy.WandbLogger.v1" |
|
project_name = "dacy-an-efficient-pipeline-for-danish" |
|
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 |
|
|
|
[training.optimizer.learn_rate] |
|
@schedules = "warmup_linear.v1" |
|
warmup_steps = 250 |
|
total_steps = 20000 |
|
initial_rate = 0.00005 |
|
|
|
[training.score_weights] |
|
pos_acc = 0.08 |
|
morph_acc = 0.08 |
|
morph_per_feat = null |
|
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 = 0.5 |
|
ents_f = 0.16 |
|
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.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] |