python - SpaCy 在 spacy-lookups-data 中找不到语言 'en' 的表 lexeme_norm

Question

我正在尝试在 SpaCy 中训练文本分类管道:

import spacy

nlp = spacy.load("en_core_web_sm")
nlp.add_pipe("textcat", last=True)
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'textcat']
with nlp.disable_pipes(*other_pipes):
    optimizer = nlp.begin_training()
    # training logic

但是，每次我调用 nlp.begin_training() ，我得到错误

ValueError: [E955] Can't find table(s) lexeme_norm for language 'en' in spacy-lookups-data. Make sure you have the package installed or provide your own lookup tables if no default lookups are available for your language.

运行 python3 -m spacy validate返回

✔ Loaded compatibility table

================= Installed pipeline packages (spaCy v3.0.3) =================
ℹ spaCy installation:
/xxx/xxx/xxx/env/lib/python3.8/site-packages/spacy

NAME             SPACY            VERSION                            
en_core_web_lg   >=3.0.0,<3.1.0   3.0.0   ✔
en_core_web_sm   >=3.0.0,<3.1.0   3.0.0   ✔

此外，我尝试安装 spacy-lookups-data没有成功。
如何解决此错误？

Answer 1

不允许调用nlp.begin_training()在预训练模型上。如果你想训练一个新模型，只需使用:nlp = spacy.blank('en')而不是 nlp = spacy.load("en_core_web_sm")但是，如果您想继续在现有模型上进行训练，调用 optimizer = nlp.create_optimizer()而不是 begin_training()