explosion spaCy Language-support Discussions
Language Support Discussions
Discuss the language data and training models for new languages
Pinned to Language Support
Discussions
-
You must be logged in to vote Problem with French parsing when using apostrophe
lang / frFrench language data and models perf / accuracyPerformance: accuracy -
You must be logged in to vote Adding Vietnamese language support for Spacy
lang / viVietnamese language data and models new languageAdding support for new languages to spaCy. -
You must be logged in to vote Using non-UD Arabic data
feat / cliFeature: Command-line interface -
You must be logged in to vote Japanese transformers-based model
enhancementFeature requests and improvements lang / jaJapanese language data and models feat / transformerFeature: Transformer -
You must be logged in to vote German lemmatizer based on outdated spelling rules
enhancementFeature requests and improvements lang / deGerman language data and models help wanted (easy)Contributions welcome! (also suited for spaCy beginners) feat / lemmatizerFeature: Rule-based and lookup lemmatization -
You must be logged in to vote NER differences in spaCy v2 and v3.
lang / enEnglish language data and models feat / nerFeature: Named Entity Recognizer -
You must be logged in to vote Wrong location detection in Spanish
lang / esSpanish language data and models feat / tokenizerFeature: Tokenizer -
You must be logged in to vote Appending morphologizer to Japanese pipeline
lang / jaJapanese language data and models -
You must be logged in to vote Errors in Chinese PKUSEG handling ascii characters
lang / zhChinese language data and models feat / tokenizerFeature: Tokenizer -
You must be logged in to vote Japanese model ja_core_news_lg training config
feat / configFeature: Training config -
You must be logged in to vote Difference in performance of postags between small and large models of portuguese
lang / ptPortuguese language data and models perf / accuracyPerformance: accuracy -
You must be logged in to vote English Sentenciser - Acronyms
feat / tokenizerFeature: Tokenizer -
You must be logged in to vote Spacy Architecture
usageGeneral spaCy usage modelsIssues related to the statistical models -
You must be logged in to vote Abbreviations Expansion
lang / esSpanish language data and models feat / tokenizerFeature: Tokenizer -
You must be logged in to vote Some sentences that consist of '&' are being cut off when performing over the model 'en_core_web_trf'
usageGeneral spaCy usage resolvedThe issue was addressed / answered -
You must be logged in to vote There is nothing or a little change after training on an existing model for dependency parser using 71 examples.
trainingTraining and updating models feat / parserFeature: Dependency Parser -
You must be logged in to vote Why can't I get the attribute 'pos' data from a new model trained from scratch?
trainingTraining and updating models feat / taggerFeature: Part-of-speech tagger feat / morphologizerFeature: Morphologizer -
You must be logged in to vote
lang / enLEMMA_ACCmissing in English modelsEnglish language data and models -
You must be logged in to vote What is [initialize] vector='model' and what are the differences between stock models?
feat / vectorsFeature: Word vectors and similarity -
You must be logged in to vote Japanese Training data (as used in the model ja_core_news_lg for example)
lang / jaJapanese language data and models -
You must be logged in to vote create new pipeline for Persian
lang / faPersian language data and models -
You must be logged in to vote Characterization of PoS accuracy
feat / taggerFeature: Part-of-speech tagger perf / accuracyPerformance: accuracy -
You must be logged in to vote Using Spacy V2 en_core_web_lg-2.3.1 model in Spacy V3
feat / taggerFeature: Part-of-speech tagger perf / accuracyPerformance: accuracy -
You must be logged in to vote zh_core_web_lg static embedding come from where?
lang / zhChinese language data and models feat / vectorsFeature: Word vectors and similarity
