JohnSnowLabs/spark-nlp-models

Models and Pipelines for the Spark NLP library

Source code at GitHub https://nlp.johnsnowlabs.com/

{
  "createdAt": "2019-06-10T12:14:12Z",
  "defaultBranch": "master",
  "description": "Models and Pipelines for the Spark NLP library",
  "fullName": "JohnSnowLabs/spark-nlp-models",
  "homepage": "https://nlp.johnsnowlabs.com/",
  "language": "Jupyter Notebook",
  "name": "spark-nlp-models",
  "pushedAt": "2021-08-12T10:05:35Z",
  "stargazersCount": 112,
  "topics": [
    "deep-learning",
    "machine-learning",
    "natural-language-processing",
    "natural-language-understanding",
    "nlp",
    "nlu",
    "spark",
    "spark-nlp"
  ],
  "updatedAt": "2025-10-03T22:23:57Z",
  "url": "https://github.com/JohnSnowLabs/spark-nlp-models"
}

Spark NLP Models

This repository is deprecated. Please use Models Hub

Caution: This repo is not maintained anymore. Please visit https://nlp.johnsnowlabs.com/models to keep track of Spark NLP models.

We use this repository to maintain our releases of pre-trained pipelines and models for the Spark NLP library.

Project’s website

Take a look at our official Spark NLP page: http://nlp.johnsnowlabs.com/ for user documentation and examples

Slack community channel

Join Slack

Open Source

Spark NLP comes with 1100+ pretrained pipelines and models in more than 192+ languages.

Some of the selected languages: Afrikaans, Arabic, Armenian, Basque, Bengali, Breton, Bulgarian, Catalan, Czech, Dutch, English, Esperanto, Finnish, French, Galician, German, Greek, Hausa, Hebrew, Hindi, Hungarian, Indonesian, Irish, Italian, Japanese, Latin, Latvian, Marathi, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Somali, Southern Sotho, Spanish, Swahili, Swedish, Tswana, Turkish, Ukrainian, Zulu

Please check out our Models Hub for the full and updated list of pre-trained models & pipelines with examples, demo, benchmark, and more

Licensed Enterprise

It is required to specify 3rd argument to pretrained(name, lang, location) function to add the location of these

Pretrained Models - Spark NLP For Healthcare

English Language, Clinical/Models Location

{Model}.pretrained({Name}, 'en', 'clinical/models')

Model	Name	Build
`AssertionDLModel`	`assertion_dl_large`	`2.5.0`	:mag:	:clipboard:	:floppy_disk:
`AssertionDLModel`	`assertion_dl`	`2.4.0`	:mag:	:clipboard:	:floppy_disk:
`AssertionDLModel`	`assertion_dl_healthcare`	`2.5.0`	:mag:	:clipboard:	[:floppy_disk:]!(s3://auxdata.johnsnowlabs.com/clinical/models/assertion_dl_healthcare_en_2.6.0_2.4_1600849811713.zip ‘Download’)
`AssertionDLModel`	`assertion_dl_biobert`	`2.6.2`	:mag:	:clipboard:	:floppy_disk:
`AssertionLogRegModel`	`assertion_ml`	`2.4.0`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_cpt_clinical`	`2.4.5`		:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_icd10cm_clinical`	`2.4.5`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_icd10cm_diseases_clinical`	`2.4.5`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_icd10cm_injuries_clinical`	`2.4.5`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_icd10cm_musculoskeletal_clinical`	`2.4.5`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_icd10cm_neoplasms_clinical`	`2.4.5`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_icd10cm_puerile_clinical`	`2.4.5`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_icd10pcs_clinical`	`2.4.5`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_icdo_clinical`	`2.4.5`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_loinc_clinical`	`2.5.0`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_rxnorm_cd_clinical`	`2.5.1`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_rxnorm_sbd_clinical`	`2.5.1`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_rxnorm_scd_clinical`	`2.5.1`	:mag:	:clipboard:	:floppy_disk:
`ChunkEntityResolverModel`	`chunkresolve_snomed_findings_clinical`	`2.5.1`	:mag:	:clipboard:	:floppy_disk:
`SentenceEntityResolverModel`	`sbiobertresolve_cpt`	`2.6.4`		:clipboard:	:floppy_disk:
`SentenceEntityResolverModel`	`sbiobertresolve_icd10cm`	`2.6.4`		:clipboard:	:floppy_disk:
`SentenceEntityResolverModel`	`sbiobertresolve_icd10pcs`	`2.6.4`		:clipboard:	:floppy_disk:
`SentenceEntityResolverModel`	`sbiobertresolve_icdo`	`2.6.4`		:clipboard:	:floppy_disk:
`SentenceEntityResolverModel`	`sbiobertresolve_rxnorm`	`2.6.4`		:clipboard:	:floppy_disk:
`SentenceEntityResolverModel`	`sbiobertresolve_snomed_auxConcepts`	`2.6.4`		:clipboard:	:floppy_disk:
`SentenceEntityResolverModel`	`sbiobertresolve_snomed_auxConcepts_int`	`2.6.4`		:clipboard:	:floppy_disk:
`SentenceEntityResolverModel`	`sbiobertresolve_snomed_findings`	`2.6.4`		:clipboard:	:floppy_disk:
`SentenceEntityResolverModel`	`sbiobertresolve_snomed_findings_int`	`2.6.4`		:clipboard:	:floppy_disk:
`ContextSpellCheckerModel`	`spellcheck_clinical`	`2.4.2`		:clipboard:	:floppy_disk:
`DeIdentificationModel`	`deidentify_rb_no_regex`	`2.5.0`		:clipboard:	:floppy_disk:
`DeIdentificationModel`	`deidentify_rb`	`2.0.2`		:clipboard:	:floppy_disk:
`DeIdentificatoinModel`	`deidentify_large`	`2.5.1`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_anatomy`	`2.4.2`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_bionlp`	`2.4.0`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_cellular`	`2.4.2`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_clinical_large`	`2.5.0`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_clinical`	`2.4.0`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_deid_enriched`	`2.5.3`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_deid_large`	`2.5.3`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_diseases`	`2.4.4`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_diseases_large`	`2.6.3`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_drugs`	`2.4.4`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_events_clinical`	`2.5.5`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_healthcare`	`2.4.4`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_jsl_enriched`	`2.4.2`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_jsl`	`2.4.2`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_medmentions_coarse`	`2.5.0`		:clipboard:	:floppy_disk:
`NerDLModel`	`ner_posology_large`	`2.4.2`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_drugs_large`	`2.6.0`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_posology_small`	`2.4.2`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_posology`	`2.4.4`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_risk_factors`	`2.4.2`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_human_phenotype_go_clinical`	`2.6.0`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_human_phenotype_gene_clinical`	`2.6.0`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_chemprot_clinical`	`2.6.0`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_ade_clinical`	`2.6.2`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_ade_healthcare`	`2.6.2`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_ade_biobert`	`2.6.2`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_ade_clinicalbert`	`2.6.2`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_bacterial_species`	`2.6.3`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_chemicals`	`2.6.3`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_clinical_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_anatomy_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_bionlp_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_cellular_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_deid_enriched_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_diseases_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_events_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_jsl_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_jsl_enriched_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_chemprot_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_human_phenotype_gene_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_human_phenotype_go_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_posology_large_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_posology_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_risk_factors_biobert`	`2.6.2`	:mag:	[:clipboard:]!(xxx)	:floppy_disk:
`NerDLModel`	`ner_anatomy_coarse_biobert`	`2.6.1`		:clipboard:	:floppy_disk:
`NerDLModel`	`ner_anatomy_coarse`	`2.6.1`		:clipboard:	:floppy_disk:
`NerDLModel`	`ner_deid_sd_large`	`2.6.3`		:clipboard:	:floppy_disk:
`NerDLModel`	`ner_aspect_based_sentiment`	`2.6.2`		:clipboard:	:floppy_disk:
`NerDLModel`	`ner_financial_contract`	`2.6.3`		:clipboard:	:floppy_disk:
`ClassifierDLModel`	`classifierdl_ade_biobert`	`2.6.2`	:mag:	:clipboard:	:floppy_disk:
`ClassifierDLModel`	`classifierdl_ade_conversational_biobert`	`2.6.2`	:mag:	:clipboard:	:floppy_disk:
`ClassifierDLModel`	`classifierdl_ade_clinicalbert`	`2.6.2`	:mag:	:clipboard:	:floppy_disk:
`ClassifierDLModel`	`classifierdl_pico_biobert`	`2.6.2`	:mag:	:clipboard:	:floppy_disk:
`PerceptronModel`	`pos_clinical`	`2.0.2`		:clipboard:	:floppy_disk:
`RelationExtractionModel`	`re_clinical`	`2.5.5`	:mag:	:clipboard:	:floppy_disk:
`RelationExtractionModel`	`re_posology`	`2.5.5`	:mag:	:clipboard:
`RelationExtractionModel`	`re_temporal_events_clinical`	`2.6.0`	:mag:	:clipboard:	:floppy_disk:
`RelationExtractionModel`	`re_temporal_events_enriched_clinical`	`2.6.0`	:mag:	:clipboard:	:floppy_disk:
`RelationExtractionModel`	`re_human_phenotype_gene_clinical`	`2.6.0`	:mag:	:clipboard:	:floppy_disk:
`RelationExtractionModel`	`re_drug_drug_interaction_clinical`	`2.6.0`	:mag:	:clipboard:	:floppy_disk:
`RelationExtractionModel`	`re_chemprot_clinical`	`2.6.0`	:mag:	:clipboard:	:floppy_disk:
`TextMatcherModel`	`textmatch_cpt_token`	`2.4.5`		:clipboard:	:floppy_disk:
`TextMatcherModel`	`textmatch_icdo_ner`	`2.4.5`		:clipboard:	:floppy_disk:
`BertSentenceEmbeddings`	`sbiobert_base_cased_mli`	`2.6.4`		:clipboard:	:floppy_disk:
`BertSentenceEmbeddings`	`sbluebert_base_uncased_mli`	`2.6.4`		:clipboard:	:floppy_disk:
`WordEmbeddingsModel`	`embeddings_clinical`	`2.4.0`		:clipboard:	:floppy_disk:
`WordEmbeddingsModel`	`embeddings_healthcare_100d`	`2.5.0`		:clipboard:	:floppy_disk:
`WordEmbeddingsModel`	`embeddings_healthcare`	`2.4.4`		:clipboard:	:floppy_disk:
`SentenceDetectorDLModel`	`sentence_detector_dl_healthcare`	`2.6.2`		:clipboard:	:floppy_disk:

Spanish Language, Clinical/Models Location

{Model}.pretrained({Name}, 'es', 'clinical/models')

Model	Name	Build
`NerDLModel`	`ner_diag_proc`	`2.5.3`	:mag:	:clipboard:	:floppy_disk:
`NerDLModel`	`ner_neoplasms`	`2.5.3`	:mag:	:clipboard:	:floppy_disk:
`WordEmbeddingsModel`	`embeddings_scielo_150d`	`2.5.0`		:clipboard:	:floppy_disk:
`WordEmbeddingsModel`	`embeddings_scielo_300d`	`2.5.0`		:clipboard:	:floppy_disk:
`WordEmbeddingsModel`	`embeddings_scielo_50d`	`2.5.0`		:clipboard:	:floppy_disk:
`WordEmbeddingsModel`	`embeddings_scielowiki_150d`	`2.5.0`		:clipboard:	:floppy_disk:
`WordEmbeddingsModel`	`embeddings_scielowiki_300d`	`2.5.0`		:clipboard:	:floppy_disk:
`WordEmbeddingsModel`	`embeddings_scielowiki_50d`	`2.5.0`		:clipboard:	:floppy_disk:

Pretrained Healthcare Pipelines

PretrainedPipeline({Name}, 'en', 'clinical/models')

Pipeline	Name	Build	lang	Description	Offline
Explain Clinical Document (type-1)	`explain_clinical_doc_carp`	`2.6.0`	`en`	a pipeline with `ner_clinical`, `assertion_dl`, `re_clinical` and `ner_posology`. It will extract clinical and medication entities, assign assertion status and find relationships between clinical entities.	Download
Explain Clinical Document (type-2)	`explain_clinical_doc_era`	`2.6.0`	`en`	a pipeline with `ner_clinical_events`, `assertion_dl` and `re_temporal_events_clinical`. It will extract clinical entities, assign assertion status and find temporal relationships between clinical entities.	Download
Explain Clinical Document (type-3)	`recognize_entities_posology`	`2.6.0`	`en`	a pipeline with `ner_posology`. It will only extract medication entities.	Download
Explain Clinical Document (type-4)	`explain_clinical_doc_ade`	`2.6.2`	`en`	a pipeline for `Adverse Drug Events (ADE)` with `ner_ade_biobert`, `assertiondl_biobert` and `classifierdl_ade_conversational_biobert`. It will extract `ADE` and `DRUG` clinical entities, assigen assertion status to `ADE` entities, and then assign ADE status to a text(`True` means ADE, `False` means not related to ADE).	Download

German Models

Model	Name	Build	lang	Offline
NER Healthcare	`ner_healthcare`	2.6.0	`de`	Download
NER Healthcare	`ner_healthcare_slim`	2.6.0	`de`	Download
Entity Resolver ICD10GM	`chunkresolve_ICD10GM`	2.6.0	`de`	Download
Entity Resolver ICD10GM	`chunkresolve_ICD10GM_2021`	2.6.0	`de`	Download
WordEmbeddings	`w2v_cc_300d`	2.6.0	`de`	Download
NER Legal	`ner_legal`	2.6.0	`de`	Download
NER Traffic	`ner_traffic`	2.6.0	`de`	Download

Contact

nlp@johnsnowlabs.com

John Snow Labs

https://johnsnowlabs.com