explosion spaCy Help-best-practices Discussions
Help: Best practices Discussions
Discuss best practices, tips and tricks
-
You must be logged in to vote how to load a model without installing it?
feat / serializeFeature: Serialization, saving and loading feat / pipelineFeature: Processing pipeline and components -
You must be logged in to vote Best practices generating and using training data for SpanCategorizer?
feat / spancatFeature: Span Categorizer -
You must be logged in to vote Is spacy.cli.download.download public API?
feat / cliFeature: Command-line interface -
You must be logged in to vote Resuming model training from last checkpoint
usageGeneral spaCy usage trainingTraining and updating models -
You must be logged in to vote How to find out what led to a DependencyMatcher result?
feat / matcherFeature: Token, phrase and dependency matcher -
You must be logged in to vote How to add new language to spacy_lookups_data?
lang / hrCroatian language data and models -
You must be logged in to vote If training a customer NER model, is there a meaningful difference between using SpanCategorizer vs. "regular" NER?
feat / nerFeature: Named Entity Recognizer feat / spancatFeature: Span Categorizer -
You must be logged in to vote Hyperparameter tuning best practices.
usageGeneral spaCy usage -
You must be logged in to vote Does spaCy support subword embeddings?
third-partyThird-party packages and services feat / vectorsFeature: Word vectors and similarity -
You must be logged in to vote How to force lemmatizing as specific part of speech?
feat / lemmatizerFeature: Rule-based and lookup lemmatization -
You must be logged in to vote add multiple entity rulers with spacy 3
feat / matcherFeature: Token, phrase and dependency matcher -
You must be logged in to vote EntityRuler additional properties
feat / matcherFeature: Token, phrase and dependency matcher resolvedThe issue was addressed / answered -
You must be logged in to vote How to prevent vocabulary from constantly growing?
perf / memoryPerformance: memory use -
You must be logged in to vote Low recall while training NER pipeline
feat / nerFeature: Named Entity Recognizer perf / accuracyPerformance: accuracy -
You must be logged in to vote Do I need null entities in my training dataset for NER?
trainingTraining and updating models feat / nerFeature: Named Entity Recognizer -
You must be logged in to vote Current recommended way to resume training V3 model?
feat / configFeature: Training config -
You must be logged in to vote Recommendation for processing very large documents
perf / memoryPerformance: memory use -
You must be logged in to vote Predicting and ranking possible next sentences in a narrative in an artificial grammar
third-partyThird-party packages and services -
You must be logged in to vote Preprocessing text and using sentencizer
perf / speedPerformance: speed feat / sentencizerFeature: Sentencizer (rule-based sentence segmenter) -
You must be logged in to vote Spacy for Commercial Use
usageGeneral spaCy usage metaMeta topics, e.g. repo organisation and issue management -
You must be logged in to vote Making the model more robust
usageGeneral spaCy usage trainingTraining and updating models perf / accuracyPerformance: accuracy -
You must be logged in to vote Improve loading time of multiple models
perf / speedPerformance: speed feat / sentencizerFeature: Sentencizer (rule-based sentence segmenter) -
You must be logged in to vote Is there any way to create a knowledge base quickly
perf / speedPerformance: speed feat / nelFeature: Named Entity linking -
You must be logged in to vote Scaling spaCy models to N user discourses
usageGeneral spaCy usage scalingScaling, serving and parallelizing spaCy -
You must be logged in to vote Any way to import 'ROOT' as a symbol?
feat / vectorsFeature: Word vectors and similarity
