explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-04 12:20:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

Format with black

Browse Source
This commit is contained in:
richardpaulhudson 2022-12-09 09:51:46 +01:00
parent 9eb1f23b95
commit abe1cb87c5
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/lemmatizer.py
View File

@ -22,8 +22,8 @@ def build_lemmatizer_model(
token input: this is used in the context of the lemmatizer to determine when to convert inputs token input: this is used in the context of the lemmatizer to determine when to convert inputs
to lowercase before processing them with the edit trees. A single normalized linear layer to lowercase before processing them with the edit trees. A single normalized linear layer
is placed between the token-to-vector component and the sigmoid output neuron, as this has is placed between the token-to-vector component and the sigmoid output neuron, as this has
been found to produce slightly better results than a direct connection. A possible intuition been found to produce slightly better results than a direct connection. A possible intuition
explaining this is that it reduces the interference between the two learning goals, explaining this is that it reduces the interference between the two learning goals,
which are linked but nonetheless distinct. which are linked but nonetheless distinct.
tok2vec (Model[List[Doc], List[Floats2d]]): The token-to-vector subnetwork. tok2vec (Model[List[Doc], List[Floats2d]]): The token-to-vector subnetwork.