mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
7f5715a081
* setting KB in the EL constructor, similar to how the model is passed on * removing wikipedia example files - moved to projects * throw an error when nlp.update is called with 2 positional arguments * rewriting the config logic in create pipe to accomodate for other objects (e.g. KB) in the config * update config files with new parameters * avoid training pipeline components that don't have a model (like sentencizer) * various small fixes + UX improvements * small fixes * set thinc to 8.0.0a9 everywhere * remove outdated comment
34 lines
1.0 KiB
Python
34 lines
1.0 KiB
Python
from pathlib import Path
|
|
|
|
from thinc.api import chain, clone, list2ragged, reduce_mean, residual
|
|
from thinc.api import Model, Maxout, Linear
|
|
|
|
from ...util import registry
|
|
from ...kb import KnowledgeBase
|
|
from ...vocab import Vocab
|
|
|
|
|
|
@registry.architectures.register("spacy.EntityLinker.v1")
|
|
def build_nel_encoder(tok2vec, nO=None):
|
|
with Model.define_operators({">>": chain, "**": clone}):
|
|
token_width = tok2vec.get_dim("nO")
|
|
output_layer = Linear(nO=nO, nI=token_width)
|
|
model = (
|
|
tok2vec
|
|
>> list2ragged()
|
|
>> reduce_mean()
|
|
>> residual(Maxout(nO=token_width, nI=token_width, nP=2, dropout=0.0))
|
|
>> output_layer
|
|
)
|
|
model.set_ref("output_layer", output_layer)
|
|
model.set_ref("tok2vec", tok2vec)
|
|
return model
|
|
|
|
|
|
@registry.assets.register("spacy.KBFromFile.v1")
|
|
def load_kb(nlp_path, kb_path) -> KnowledgeBase:
|
|
vocab = Vocab().from_disk(Path(nlp_path) / "vocab")
|
|
kb = KnowledgeBase(vocab=vocab)
|
|
kb.load_bulk(kb_path)
|
|
return kb
|