explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

add types of Tok2Vec embedding layers

Browse Source
This commit is contained in:
svlandeg 2020-10-01 09:20:09 +02:00
parent 64d90039a1
commit 5121972930
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/ml/models/tok2vec.py
View File

@ -93,7 +93,7 @@ def build_Tok2Vec_model(
@registry.architectures.register("spacy.MultiHashEmbed.v1")
def MultiHashEmbed(
width: int, rows: int, also_embed_subwords: bool, also_use_static_vectors: bool
):
) -> Model[List[Doc], List[Floats2d]]:
"""Construct an embedding layer that separately embeds a number of lexical
attributes using hash embedding, concatenates the results, and passes it
through a feed-forward subnetwork to build a mixed representations.
@ -166,7 +166,7 @@ def MultiHashEmbed(
@registry.architectures.register("spacy.CharacterEmbed.v1")
def CharacterEmbed(
width: int, rows: int, nM: int, nC: int, also_use_static_vectors: bool
):
) -> Model[List[Doc], List[Floats2d]]:
"""Construct an embedded representation based on character embeddings, using
a feed-forward network. A fixed number of UTF-8 byte characters are used for
each word, taken from the beginning and end of the word equally. Padding is