Contextual SpellChecker Clinical

Description

Implements Noisy Channel Model Spell Algorithm. Correction candidates are extracted combining context information and word information

Live Demo Open in Colab Copy S3 URI

How to use

model = ContextSpellCheckerModel.pretrained("spellcheck_clinical","en","clinical/models")
	.setInputCols("token")
	.setOutputCol("spell")
val model = ContextSpellCheckerModel.pretrained("spellcheck_clinical","en","clinical/models")
	.setInputCols("token")
	.setOutputCol("spell")
import nlu
nlu.load("en.spell.clinical").predict("""Put your text here.""")

Model Information

Name: spellcheck_clinical
Type: ContextSpellCheckerModel
Compatibility: 2.4.2
License: Licensed
Edition: Official
Input labels: [token]
Output labels: [spell]
Language: en
Dependencies: embeddings_clinical

Data Source

Trained with augmented version of i2b2 and PubMed datasets.