Drug Spell Checker

Description

This model detects and corrects spelling errors of drugs in your input text based on Norvig’s approach.

Predicted Entities

Copy S3 URI

How to use

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

tokenizer = Tokenizer()\
.setInputCols("document")\
.setOutputCol("token")

spell = NorvigSweetingModel.pretrained("spellcheck_drug_norvig", "en", "clinical/models")\
.setInputCols("token")\
.setOutputCol("spell")\


pipeline = Pipeline(
stages = [
documentAssembler,    
tokenizer,
spell])

model = pipeline.fit(spark.createDataFrame([['']]).toDF('text'))
lp = LightPipeline(model)

result = lp.annotate("You have to take Neutrcare and colfosrinum and a bit of Fluorometholne & Ribotril")
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")

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

val spell = new NorvigSweetingModel.pretrained("spellcheck_drug_norvig", "en", "clinical/models")
.setInputCols("token")
.setOutputCol("spell")

val pipeline = new Pipeline().setStages(Array(documentAssembler,tokenizer,spell))

val model = pipeline.fit(spark.createDataFrame([['']]).toDF('text'))
val lp = new LightPipeline(model)

val result = lp.annotate("You have to take Neutrcare and colfosrinum and a bit of Fluorometholne & Ribotril")
import nlu
nlu.load("en.spell.drug_norvig").predict("""You have to take Neutrcare and colfosrinum and a bit of Fluorometholne & Ribotril""")

Results

Original text  : You have to take Neutrcare and colfosrinum and a bit of fluorometholne & Ribotril

Corrected text : You have to take Neutracare and colforsinum and a bit of fluorometholone & Rivotril

Model Information

Model Name: spellcheck_drug_norvig
Compatibility: Healthcare NLP 3.2.2+
License: Licensed
Edition: Official
Input Labels: [token]
Output Labels: [spell]
Language: en
Case sensitive: true