Questions tagged [spacy-3]
For questions specific to spaCy version 3, an Industrial-Strength Natural Language Processing tool in Python. Use the more generic tag `spacy` for general questions about the spaCy.
spacy-3
347
questions
0
votes
0
answers
32
views
Memory usage when using spaCy Doc extensions
Issue
Before preprocessing my data with spaCy, I typically have my data stored in a Pandas Series. Since I'd like to preserve the index for each document before serializing my Docs, I decided to use ...
0
votes
0
answers
26
views
spacy-llm & SpanCat for address parsing
I'm currently developing a project to standardize and correct a dataset of inconsistently formatted addresses using spaCy-LLM and spaCy.SpanCat.v3. The goal is to train a model on examples of ...
0
votes
0
answers
14
views
Is there any possibility to integrate NER and Textcat Multilabel Models in the same Pipeline
I am working on extracting information from raw text and have created an NER model with 6 entities. I want to pass the output of the NER model to textcat multilabel models. Specifically, I have ...
1
vote
0
answers
37
views
What is causing this error in the official spacy classy classification example?
I've been trying to learn how to use spacy and now I want to learn how to use classy classification, however, the example of classy shown in the official spacy webpage is not working. Here's the code ...
1
vote
0
answers
22
views
Spacy detect correctly GPE
I've a set of string where I shall detetect the country its belongs to, referring to detected GPE.
sentences = [
"I watched TV in germany",
"Mediaset ITA canale 5",
&...
0
votes
1
answer
72
views
Cannot use GPU for custom spaCy NER model
I'm trying to make a custom NER model using spaCy. When I try to leverage gpu it throws an error stating that Cupy is not installed even though it is. Attaching relevant info below.
> ubuntu@:~$ ...
0
votes
0
answers
39
views
Custom Named Entity Recognition (NER) Model with spaCy V3
This is my first time building a custom model with SPACY NER.
# Define a function to create spaCy DocBin objects from the annotated data
def get_spacy_doc(file, data):
# Create a blank spaCy ...
0
votes
1
answer
45
views
SpaCy transformer NER training – zero loss on transformer, not trained
I am training a SpaCy pipeline with ['transformer', 'ner'] components, ner trains well, but transformer is stuck on 0 loss, and, I am assuming, is not training.
Here is my config:
[paths]
vectors = &...
0
votes
2
answers
25
views
Spacy - return nouns without the grammatical articles
In Spacy, when we request the nouns, the grammatical articles (ex.: "the", "one", "a") are also presented
import spacy
nlp_en = spacy.load('en_core_web_sm') # v3.7.1
doc ...
1
vote
1
answer
54
views
Load Spacy language module according to detected language
All around I see this example related to the package LanguageDetector
import spacy
from spacy.language import Language
from spacy_langdetect import LanguageDetector
def get_lang_detector(nlp, name):
...
0
votes
0
answers
44
views
Custom spaCy NLP model inside Rasa SpacyNLP pipeline
I am trying to integrate a custom NER model for my Rasa chatbot but I am having a hard time understanding how the SpacyTokenizer and SpacyFeaturizer in the SpacyNLP pipeline in Rasa are related to my ...
0
votes
0
answers
8
views
Custom pipeline component for Spacy does not receive part of speach tags
I add a custom pipeline component after tagger to Spacy model. It does not receive pos_ and tag_ information.
Here the code:
nlp = spacy.load("en_core_web_trf")
@Language.component("...
0
votes
1
answer
63
views
Can I monitor progress of spacy parsing?
I have a simple program to process English text with spacy and output some of the info about the tokens. For a big text it takes a long time for spacy to process it. Is there a way to see how far the ...
0
votes
0
answers
31
views
Rasa: Borfront compability troubleshooting
I use an open source product - Botfront, which uses Rasa version 2.3.3 and Rasa SDK 2.3.1. I need to train a model in Russian using Spacy NLP. By default, Spacy version 2.2.4 is installed in the Rasa ...
0
votes
0
answers
33
views
Trying to understand how batching works with Thinc models
Since many of the Thinc layers require a Float2D as input, I've been struggling to understand how to pass a batch of tokenized text, where [batch_size, max_seq_length, embedding_size] are the ...