Edit on GitHub
  • John Snow Labs
  • Dec 21, 2025

Vehicle Identifier Number Contextual Parser Model

  • en
  • contextualparser
  • licensed
  • clinical
  • vin

Description

This model, extracts vehicle identifier number entities from clinical texts.

Copy S3 URI

How to use



document_assembler = DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")

sentence_detector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")\
    .setInputCols(["document"])\
    .setOutputCol("sentence")

tokenizer = Tokenizer()\
    .setInputCols(["sentence"])\
    .setOutputCol("token")

vin_contextual_parser = ContextualParserModel.pretrained("vin_parser","en","clinical/models")\
    .setInputCols(["sentence", "token"])\
    .setOutputCol("chunk_vin")

chunk_converter = ChunkConverter()\
    .setInputCols(["chunk_vin"])\
    .setOutputCol("ner_chunk")

parserPipeline = Pipeline(stages=[
        document_assembler,
        sentence_detector,
        tokenizer,
        vin_contextual_parser,
        chunk_converter
        ])

model = parserPipeline.fit(spark.createDataFrame([[""]]).toDF("text"))

sample_text = """Name : Hendrickson, Ora, Record date: 2093-01-13, # 719435.
Dr. John Green, ID: 1231511863, IP 203.120.223.13.
He is a 60-year-old male was admitted to the Day Hospital for cystectomy on 01/13/93.
Patient's VIN : 1HGBH41JXMN109286, VIN 4Y1SL65848Z411439, VIN 1HGCM82633A123456 - VIN JH4KA7560MC012345 - VIN 5YJSA1E14HF123456
SSN #333-44-6666, Driver's license no:A334455B, plate 34NLP34.
Phone (302) 786-5227, 0295 Keats Street, San Francisco, E-MAIL: smith@gmail.com."""

result = model.transform(spark.createDataFrame([[sample_text]]).toDF("text"))






document_assembler = nlp.DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")

sentence_detector = nlp.SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")\
    .setInputCols(["document"])\
    .setOutputCol("sentence")

tokenizer = nlp.Tokenizer()\
    .setInputCols(["sentence"])\
    .setOutputCol("token")

vin_contextual_parser = medical.ContextualParserModel.pretrained("vin_parser","en","clinical/models")\
    .setInputCols(["sentence", "token"])\
    .setOutputCol("chunk_vin")

chunk_converter = medical.ChunkConverter()\
    .setInputCols(["chunk_vin"])\
    .setOutputCol("ner_chunk")

parserPipeline = nlp.Pipeline(stages=[
        document_assembler,
        sentence_detector,
        tokenizer,
        vin_contextual_parser,
        chunk_converter
        ])

model = parserPipeline.fit(spark.createDataFrame([[""]]).toDF("text"))

sample_text = """Name : Hendrickson, Ora, Record date: 2093-01-13, # 719435.
Dr. John Green, ID: 1231511863, IP 203.120.223.13.
He is a 60-year-old male was admitted to the Day Hospital for cystectomy on 01/13/93.
Patient's VIN : 1HGBH41JXMN109286, VIN 4Y1SL65848Z411439, VIN 1HGCM82633A123456 - VIN JH4KA7560MC012345 - VIN 5YJSA1E14HF123456
SSN #333-44-6666, Driver's license no:A334455B, plate 34NLP34.
Phone (302) 786-5227, 0295 Keats Street, San Francisco, E-MAIL: smith@gmail.com."""

result = model.transform(spark.createDataFrame([[sample_text]]).toDF("text"))




val document_assembler = new DocumentAssembler()
    .setInputCol("text")
    .setOutputCol("document")

val sentence_detector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")
    .setInputCols("document")
    .setOutputCol("sentence")

val tokenizer = new Tokenizer()
    .setInputCols("sentence")
    .setOutputCol("token")

val vin_contextual_parser = ContextualParserModel.pretrained("vin_parser","en","clinical/models")
    .setInputCols(Array("sentence", "token"))
    .setOutputCol("chunk_vin")

val chunk_converter = new ChunkConverter()
    .setInputCols("chunk_vin")
    .setOutputCol("ner_chunk")

val parserPipeline = new Pipeline().setStages(Array(
        document_assembler,
        sentence_detector,
        tokenizer,
        vin_contextual_parser,
        chunk_converter
))


val sample_text = """Name : Hendrickson, Ora, Record date: 2093-01-13, # 719435.
Dr. John Green, ID: 1231511863, IP 203.120.223.13.
He is a 60-year-old male was admitted to the Day Hospital for cystectomy on 01/13/93.
Patient's VIN : 1HGBH41JXMN109286, VIN 4Y1SL65848Z411439, VIN 1HGCM82633A123456 - VIN JH4KA7560MC012345 - VIN 5YJSA1E14HF123456
SSN #333-44-6666, Driver's license no:A334455B, plate 34NLP34.
Phone (302) 786-5227, 0295 Keats Street, San Francisco, E-MAIL: smith@gmail.com."""

val data = Seq(sample_text).toDF("text")

val results = parserPipeline.fit(data).transform(data)

Results



| chunk             |   begin |   end | label   |
|:------------------|--------:|------:|:--------|
| 1HGBH41JXMN109286 |     213 |   229 | VIN     |
| 4Y1SL65848Z411439 |     236 |   252 | VIN     |
| 1HGCM82633A123456 |     259 |   275 | VIN     |
| JH4KA7560MC012345 |     283 |   299 | VIN     |
| 5YJSA1E14HF123456 |     307 |   323 | VIN     |

Model Information

Model Name: vin_parser
Compatibility: Healthcare NLP 6.2.2+
License: Licensed
Edition: Official
Input Labels: [document, token_doc]
Output Labels: [entity_vin_code]
Language: en
Size: 4.4 KB
Case sensitive: false