Default Component References
See and also the John Snow Labs Modelhub and also the John Snow Labs Model Repository for further information about the models and pipelines.
Each String in the NLP reference column can be passed to nlp.load() to get the corresponding model wrapped inside a NLP Pipeline.
Language | nlp.load() Reference | Spark NLP Reference | Component Type |
---|---|---|---|
English | yake | yake | pipe |
English | xlnet | xlnet_base_cased | pipe |
English | use | tfhub_use | pipe |
English | toxic | multiclassifierdl_use_toxic | pipe |
English | tokenize | spark_nlp_tokenizer | pipe |
English | t5 | t5_base | pipe |
English | summarize | t5_base | pipe |
English | stopwords | stopwords_en | pipe |
English | stem | stemmer | pipe |
English | spell | spellcheck_dl | pipe |
English | spell.symmetric | spellcheck_sd | pipe |
English | spell.norivg | spellcheck_norvig | pipe |
English | spam | classifierdl_use_spam | pipe |
English | sentiment | sentimentdl_glove_imdb | pipe |
English | sentiment.vivekn | sentiment_vivekn | pipe |
English | sentiment.twitter | analyze_sentimentdl_use_twitter | model |
English | sentiment.twitter.use | analyze_sentimentdl_use_twitter | model |
English | sentiment.imdb | analyze_sentimentdl_use_imdb | model |
English | sentiment.imdb.use | analyze_sentimentdl_use_imdb | pipe |
English | sentiment.imdb.glove | sentimentdl_glove_imdb | pipe |
English | sentence_detector | sentence_detector_dl | pipe |
English | sentence_detector.pragmatic | pragmatic_sentence_detector | pipe |
English | sentence_detector.deep | sentence_detector_dl | model |
English | sarcasm | classifierdl_use_sarcasm | model |
English | questions | classifierdl_use_trec50 | model |
English | pos | pos_anc | model |
English | pos.ud_ewt | pos_ud_ewt | model |
English | pos.anc | pos_anc | model |
English | norm_document | normalizer | model |
English | norm | normalizer | model |
English | ngram | ngram | model |
English | ner | onto_recognize_entities_sm | model |
English | ner.onto | onto_recognize_entities_sm | model |
English | ner.onto.sm | onto_recognize_entities_sm | model |
English | ner.onto.glove.6B_300d | onto_300 | model |
English | ner.onto.glove.6B_100d | onto_100 | model |
English | ner.dl | recognize_entities_dl | model |
English | ner.dl.glove.6B_100d | ner_dl | model |
English | ner.dl.bert | ner_dl_bert | model |
English | ner.conll | recognize_entities_dl | model |
English | ner.bert | recognize_entities_bert | model |
English | match.chunks | match_chunks | model |
English | lemma | lemma_antbnc | model |
English | lemma.antbnc | lemma_antbnc | model |
English | lang | detect_language_375 | model |
English | grammar_correctness | t5_base | model |
English | glove | glove_100d | model |
English | explain | explain_document_ml | model |
English | explain.ml | explain_document_ml | model |
English | explain.dl | explain_document_dl | model |
English | emotion | classifierdl_use_emotion | model |
English | embed_sentence | tfhub_use | model |
English | embed_sentence.use_lg | tfhub_use_lg | model |
English | embed_sentence.use | tfhub_use | model |
English | embed_sentence.tfhub_use_lg | tfhub_use_lg | model |
English | embed_sentence.tfhub_use | tfhub_use | model |
English | embed_sentence.small_bert_L2_128 | sent_small_bert_L2_128 | model |
English | embed_sentence.electra | sent_electra_small_uncased | model |
English | embed_sentence.bert | sent_small_bert_L2_128 | model |
English | embed_chunk | chunk_embeddings | model |
English | embed | glove_100d | model |
English | embed.xlnet_large_cased | xlnet_large_cased | model |
English | embed.xlnet_base_cased | xlnet_base_cased | model |
English | embed.xlnet | xlnet_base_cased | model |
English | embed.glove | glove_100d | model |
English | embed.glove.840B_300 | glove_840B_300 | model |
English | embed.glove.100d | glove_100d | model |
English | embed.elmo | elmo | model |
English | embed.electra | electra_small_uncased | model |
English | embed.biobert_pubmed_pmc_base_cased | biobert_pubmed_pmc_base_cased | model |
English | embed.biobert_pubmed_large_cased | biobert_pubmed_large_cased | model |
English | embed.biobert_pubmed_base_cased | biobert_pubmed_base_cased | model |
English | embed.biobert_pmc_base_cased | biobert_pmc_base_cased | model |
English | embed.biobert_discharge_base_cased | biobert_discharge_base_cased | model |
English | embed.biobert_clinical_base_cased | biobert_clinical_base_cased | model |
English | embed.biobert | biobert_pubmed_base_cased | model |
English | embed.bert_large_uncased | bert_large_uncased | model |
English | embed.bert_large_cased | bert_large_cased | model |
English | embed.bert_base_uncased | bert_base_uncased | model |
English | embed.bert_base_cased | bert_base_cased | model |
English | embed.bert | bert_base_uncased | model |
English | embed.albert_xxlarge_uncased | albert_xxlarge_uncased | model |
English | embed.albert_xlarge_uncased | albert_xlarge_uncased | model |
English | embed.albert_large_uncased | albert_large_uncased | model |
English | embed.albert_base_uncased | albert_base_uncased | model |
English | elmo | elmo | model |
English | electra | electra_small_uncased | model |
English | e2e | multiclassifierdl_use_e2e | model |
English | dependency | dependency_conllu | model |
English | dep | dependency_typed_conllu | model |
English | dep.untyped | dependency_conllu | model |
English | dep.untyped.conllu | dependency_conllu | model |
English | dep.typed | dependency_typed_conllu | model |
English | dep.typed.conllu | dependency_typed_conllu | model |
English | cyberbullying | classifierdl_use_cyberbullying | model |
English | covidbert | covidbert_large_uncased | model |
English | clean.stop | clean_stop | model |
English | clean.slang | clean_slang | model |
English | classify | analyze_sentiment | model |
English | classify.trec6 | classifierdl_use_trec6 | model |
English | classify.trec6.use | classifierdl_use_trec6 | model |
English | classify.trec50 | classifierdl_use_trec50 | model |
English | classify.trec50.use | classifierdl_use_trec50 | model |
English | classify.spam | classifierdl_use_spam | model |
English | classify.spam.use | classifierdl_use_spam | model |
English | classify.sentiment_t5 | t5_base | model |
English | classify.sarcasm | classifierdl_use_sarcasm | model |
English | classify.sarcasm.use | classifierdl_use_sarcasm | model |
English | classify.questions | classifierdl_use_trec50 | model |
English | classify.lang | detect_language_375 | model |
English | classify.fakenews | classifierdl_use_fakenews | model |
English | classify.fakenews.use | classifierdl_use_fakenews | model |
English | classify.emotion | classifierdl_use_emotion | model |
English | classify.emotion.use | classifierdl_use_emotion | model |
English | classify.cyberbullying | classifierdl_use_cyberbullying | model |
English | classify.cyberbullying.use | classifierdl_use_cyberbullying | model |
English | chunk | default_chunker | model |
English | biobert | biobert_pubmed_base_cased | model |
English | bert | small_bert_L2_128 | model |
English | answer_question | t5_base | model |
English | albert | albert_base_uncased | model |
Model references
Pipeline references
Healthcare Model references
Healthcare Pipeline references
PREVIOUSNLP Utilities