235 lines
5.0 KiB
INI
235 lines
5.0 KiB
INI
# fa_dep_news_md — tagger, morphologizer, trainable_lemmatizer, parser, WITH static vectors.
|
|
#
|
|
# Byte-identical to configs/fa_dep_news_sm.cfg except:
|
|
# - [components.tok2vec.model.embed] include_static_vectors: false -> true
|
|
#
|
|
# Everything else (seed, widths, rows, batcher, patience, eval_frequency) is held constant so
|
|
# the sm/md delta measures the floret vectors and nothing else.
|
|
#
|
|
# Vectors are supplied at train time via --paths.vectors, pointing at the fa_floret table
|
|
# (50k rows x 300d, floret mode, minn=maxn=5, hash_count=2) trained on 400k Persian documents.
|
|
# floret has no OOV: every string hashes into the table, which is the point for Persian, where
|
|
# ZWNJ inconsistency (میرود / میرود / می رود) would shatter a classic word table.
|
|
#
|
|
# No `ner` here by design; see configs/fa_ner_md.cfg and project.yml.
|
|
|
|
[paths]
|
|
train = null
|
|
dev = null
|
|
vectors = null
|
|
init_tok2vec = null
|
|
|
|
[system]
|
|
gpu_allocator = null
|
|
seed = 0
|
|
|
|
[nlp]
|
|
lang = "fa"
|
|
pipeline = ["tok2vec", "tagger", "morphologizer", "trainable_lemmatizer", "parser"]
|
|
batch_size = 1000
|
|
disabled = []
|
|
before_creation = null
|
|
after_creation = null
|
|
after_pipeline_creation = null
|
|
|
|
[corpora]
|
|
|
|
[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 = 0
|
|
max_steps = 20000
|
|
eval_frequency = 400
|
|
frozen_components = []
|
|
annotating_components = []
|
|
before_to_disk = null
|
|
before_update = null
|
|
|
|
[initialize]
|
|
vectors = ${paths.vectors}
|
|
init_tok2vec = ${paths.init_tok2vec}
|
|
vocab_data = null
|
|
lookups = null
|
|
before_init = null
|
|
after_init = null
|
|
|
|
[components]
|
|
|
|
[pretraining]
|
|
|
|
[nlp.tokenizer]
|
|
@tokenizers = "spacy.Tokenizer.v1"
|
|
|
|
[nlp.vectors]
|
|
@vectors = "spacy.Vectors.v1"
|
|
|
|
[corpora.train]
|
|
@readers = "spacy.Corpus.v1"
|
|
path = ${paths.train}
|
|
max_length = 0
|
|
gold_preproc = false
|
|
limit = 0
|
|
augmenter = null
|
|
|
|
[corpora.dev]
|
|
@readers = "spacy.Corpus.v1"
|
|
path = ${paths.dev}
|
|
max_length = 0
|
|
gold_preproc = false
|
|
limit = 0
|
|
augmenter = 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 = 1e-08
|
|
learn_rate = 0.001
|
|
|
|
[training.batcher]
|
|
@batchers = "spacy.batch_by_words.v1"
|
|
discard_oversize = false
|
|
tolerance = 0.2
|
|
get_length = null
|
|
|
|
[training.logger]
|
|
@loggers = "spacy.ConsoleLogger.v1"
|
|
progress_bar = false
|
|
|
|
[training.score_weights]
|
|
tag_acc = 0.25
|
|
pos_acc = 0.12
|
|
tag_micro_p = null
|
|
tag_micro_r = null
|
|
tag_micro_f = null
|
|
morph_acc = 0.12
|
|
morph_per_feat = null
|
|
lemma_acc = 0.25
|
|
dep_uas = 0.12
|
|
dep_las = 0.12
|
|
dep_las_per_type = null
|
|
sents_p = null
|
|
sents_r = null
|
|
sents_f = 0.0
|
|
|
|
[initialize.tokenizer]
|
|
|
|
[initialize.components]
|
|
|
|
[components.tok2vec]
|
|
factory = "tok2vec"
|
|
|
|
[components.tagger]
|
|
factory = "tagger"
|
|
label_smoothing = 0.05
|
|
overwrite = false
|
|
neg_prefix = "!"
|
|
|
|
[components.morphologizer]
|
|
factory = "morphologizer"
|
|
label_smoothing = 0.05
|
|
overwrite = true
|
|
extend = false
|
|
|
|
[components.trainable_lemmatizer]
|
|
factory = "trainable_lemmatizer"
|
|
backoff = "orth"
|
|
min_tree_freq = 3
|
|
overwrite = false
|
|
top_k = 1
|
|
|
|
[components.parser]
|
|
factory = "parser"
|
|
moves = null
|
|
update_with_oracle_cut_size = 100
|
|
learn_tokens = false
|
|
min_action_freq = 30
|
|
|
|
[training.batcher.size]
|
|
@schedules = "compounding.v1"
|
|
start = 100
|
|
stop = 1000
|
|
compound = 1.001
|
|
t = 0.0
|
|
|
|
[components.tok2vec.model]
|
|
@architectures = "spacy.Tok2Vec.v2"
|
|
|
|
[components.tagger.model]
|
|
@architectures = "spacy.Tagger.v2"
|
|
nO = null
|
|
normalize = false
|
|
|
|
[components.tagger.scorer]
|
|
@scorers = "spacy.tagger_scorer.v1"
|
|
|
|
[components.morphologizer.model]
|
|
@architectures = "spacy.Tagger.v2"
|
|
nO = null
|
|
normalize = false
|
|
|
|
[components.morphologizer.scorer]
|
|
@scorers = "spacy.morphologizer_scorer.v1"
|
|
|
|
[components.trainable_lemmatizer.model]
|
|
@architectures = "spacy.Tagger.v2"
|
|
nO = null
|
|
normalize = false
|
|
|
|
[components.trainable_lemmatizer.scorer]
|
|
@scorers = "spacy.lemmatizer_scorer.v1"
|
|
|
|
[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.scorer]
|
|
@scorers = "spacy.parser_scorer.v1"
|
|
|
|
[components.tok2vec.model.embed]
|
|
@architectures = "spacy.MultiHashEmbed.v2"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE"]
|
|
rows = [5000, 1000, 2500, 2500]
|
|
include_static_vectors = true
|
|
|
|
[components.tok2vec.model.encode]
|
|
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
|
width = 96
|
|
depth = 4
|
|
window_size = 1
|
|
maxout_pieces = 3
|
|
|
|
[components.tagger.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
upstream = "*"
|
|
|
|
[components.morphologizer.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
upstream = "*"
|
|
|
|
[components.trainable_lemmatizer.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
upstream = "*"
|
|
|
|
[components.parser.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
upstream = "*" |