From b854bca15c0e4cf62d2e1c0f896dc1e6a454c099 Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Thu, 1 Oct 2020 22:17:58 +0200 Subject: [PATCH] Default to LOWER in character embed --- spacy/ml/models/tok2vec.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spacy/ml/models/tok2vec.py b/spacy/ml/models/tok2vec.py index 888dc9caa..907a7a293 100644 --- a/spacy/ml/models/tok2vec.py +++ b/spacy/ml/models/tok2vec.py @@ -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, - feature: Union[int, str]="NORM" + feature: Union[int, str]="LOWER" ): """Construct an embedded representation based on character embeddings, using a feed-forward network. A fixed number of UTF-8 byte characters are used for