|
[paths] |
|
train = "corpus/train/grc_proiel-ud-train.spacy" |
|
dev = "corpus/dev/grc_proiel-ud-dev.spacy" |
|
vectors = null |
|
init_tok2vec = null |
|
|
|
[system] |
|
gpu_allocator = null |
|
seed = 0 |
|
|
|
[nlp] |
|
lang = "grc" |
|
pipeline = ["tok2vec","morphologizer","tagger","parser","senter","lemmatizer","attribute_ruler"] |
|
batch_size = 128 |
|
disabled = [] |
|
before_creation = null |
|
after_creation = null |
|
after_pipeline_creation = null |
|
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} |
|
|
|
[components] |
|
|
|
[components.attribute_ruler] |
|
factory = "attribute_ruler" |
|
scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"} |
|
validate = false |
|
|
|
[components.lemmatizer] |
|
factory = "trainable_lemmatizer" |
|
backoff = "orth" |
|
min_tree_freq = 1 |
|
overwrite = false |
|
scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"} |
|
top_k = 5 |
|
|
|
[components.lemmatizer.model] |
|
@architectures = "spacy.Tagger.v2" |
|
nO = null |
|
normalize = false |
|
|
|
[components.lemmatizer.model.tok2vec] |
|
@architectures = "spacy.HashEmbedCNN.v2" |
|
pretrained_vectors = false |
|
width = 96 |
|
depth = 4 |
|
embed_size = 2000 |
|
window_size = 1 |
|
maxout_pieces = 3 |
|
subword_features = true |
|
|
|
[components.morphologizer] |
|
factory = "morphologizer" |
|
extend = false |
|
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.Tok2VecListener.v1" |
|
width = ${components.tok2vec.model.encode.width} |
|
upstream = "tok2vec" |
|
|
|
[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 = ${components.tok2vec.model.encode.width} |
|
upstream = "tok2vec" |
|
|
|
[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.HashEmbedCNN.v2" |
|
pretrained_vectors = null |
|
width = 12 |
|
depth = 1 |
|
embed_size = 2000 |
|
window_size = 1 |
|
maxout_pieces = 2 |
|
subword_features = true |
|
|
|
[components.tagger] |
|
factory = "tagger" |
|
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 = ${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 = false |
|
|
|
[components.tok2vec.model.encode] |
|
@architectures = "spacy.MaxoutWindowEncoder.v2" |
|
width = 256 |
|
depth = 8 |
|
window_size = 1 |
|
maxout_pieces = 3 |
|
|
|
[corpora] |
|
|
|
[corpora.dev] |
|
@readers = "spacy.Corpus.v1" |
|
path = ${paths.dev} |
|
max_length = 0 |
|
gold_preproc = false |
|
limit = 0 |
|
augmenter = null |
|
|
|
[corpora.train] |
|
@readers = "spacy.Corpus.v1" |
|
path = ${paths.train} |
|
max_length = 0 |
|
gold_preproc = false |
|
limit = 0 |
|
augmenter = null |
|
|
|
[training] |
|
dev_corpus = "corpora.dev" |
|
train_corpus = "corpora.train" |
|
seed = ${system.seed} |
|
gpu_allocator = ${system.gpu_allocator} |
|
dropout = 0.1 |
|
accumulate_gradient = 1 |
|
patience = 5000 |
|
max_epochs = 0 |
|
max_steps = 20000 |
|
eval_frequency = 200 |
|
frozen_components = ["lemmatizer","senter"] |
|
annotating_components = [] |
|
before_to_disk = null |
|
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.WandbLogger.v3" |
|
project_name = "proiel" |
|
remove_config_values = ["paths.train","paths.dev","corpora.train.path","corpora.dev.path"] |
|
log_dataset_dir = "./corpus" |
|
model_log_interval = 1000 |
|
entity = null |
|
run_name = null |
|
|
|
[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] |
|
pos_acc = 0.06 |
|
morph_acc = 0.06 |
|
morph_per_feat = null |
|
tag_acc = 0.12 |
|
dep_uas = 0.06 |
|
dep_las = 0.06 |
|
dep_las_per_type = null |
|
sents_p = null |
|
sents_r = null |
|
sents_f = null |
|
lemma_acc = 0.64 |
|
|
|
[pretraining] |
|
|
|
[initialize] |
|
vectors = ${paths.vectors} |
|
init_tok2vec = ${paths.init_tok2vec} |
|
vocab_data = null |
|
lookups = null |
|
before_init = null |
|
after_init = null |
|
|
|
[initialize.components] |
|
|
|
[initialize.components.attribute_ruler] |
|
|
|
[initialize.components.attribute_ruler.patterns] |
|
@readers = "srsly.read_json.v1" |
|
path = "data/augments/attribute_ruler_patterns.json" |
|
|
|
[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.tokenizer] |