config.cfg

[paths]
train = "train.spacy"
dev = "dev.spacy"
vectors = "./vectors"
init_tok2vec = null

[system]
gpu_allocator = null
seed = 0

[nlp]
lang = "fr"
pipeline = ["presque_normalizer","tokentype","morphologizer","viceverser_lemmatizer","sentencizer","parser"]
batch_size = 1000
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
vectors = {"@vectors":"spacy.Vectors.v1"}
tokenizer = {"@tokenizers":"quelquhui_tokenizer"}

[components]

[components.morphologizer]
factory = "morphologizer"
extend = false
label_smoothing = 0.05
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.Tok2Vec.v2"

[components.morphologizer.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = ${components.morphologizer.model.tok2vec.encode.width}
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,1000,2500,2500]
include_static_vectors = true

[components.morphologizer.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 256
depth = 8
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.HashEmbedCNN.v2"
pretrained_vectors = null
width = 96
depth = 4
embed_size = 2000
window_size = 1
maxout_pieces = 3
subword_features = false

[components.presque_normalizer]
factory = "presque_normalizer"
fn_agg_suff = null
suff_sep_char = "\u00b7"
use_default_word_list = true
words_files = []

[components.presque_normalizer.exc]

[components.sentencizer]
factory = "sentencizer"
overwrite = false
punct_chars = ["\n","!","?",":",".","..."]
scorer = {"@scorers":"spacy.senter_scorer.v1"}

[components.tokentype]
factory = "tokentype"
extname = "tokentype"

[components.viceverser_lemmatizer]
factory = "viceverser_lemmatizer"

[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 = 1600
max_epochs = 10
max_steps = 20000
eval_frequency = 200
frozen_components = []
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.ConsoleLogger.v1"
progress_bar = false

[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 = 0.25
morph_acc = 0.25
morph_per_feat = null
sents_f = 0.0
sents_p = null
sents_r = null
dep_uas = 0.25
dep_las = 0.25
dep_las_per_type = null

[pretraining]

[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
after_init = null
before_init = {"@callbacks":"space_tokenizer"}

[initialize.components]

[initialize.tokenizer]