Description
Spell Checker is a sequence-to-sequence pipeline that detects and corrects spelling errors in your input text. It’s based on Levenshtein Automaton for generating candidate corrections and a Neural Language Model for ranking corrections. You can download the pretrained pipeline that comes ready to use.
How to use
In order to use this pretrained pipeline, you need to just provide the text to be checked.
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline('check_spelling_dl', lang='en')
result = pipeline.fullAnnotate("During the summer we have the hottest ueather. I have a black ueather jacket, so nice.I intrduce you to my sister, she is called ueather.")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("check_spelling_dl", lang = "en")
val result = pipeline.fullAnnotate("During the summer we have the hottest ueather. I have a black ueather jacket, so nice.I intrduce you to my sister, she is called ueather.")
import nlu
nlu.load("en.spell").predict("""During the summer we have the hottest ueather. I have a black ueather jacket, so nice.I intrduce you to my sister, she is called ueather.""")
Results
[('During', 'During'),
('the', 'the'),
('summer', 'summer'),
('we', 'we'),
('have', 'have'),
('the', 'the'),
('hottest', 'hottest'),
('ueather', 'weather'),
('.', '.'),
('I', 'I'),
('have', 'have'),
('a', 'a'),
('black', 'black'),
('ueather', 'leather'),
('jacket', 'jacket'),
(',', ','),
('so', 'so'),
('nice', 'nice'),
('.', '.'),
('I', 'I'),
('intrduce', 'introduce'),
('you', 'you'),
('to', 'to'),
('my', 'my'),
('sister', 'sister'),
(',', ','),
('she', 'she'),
('is', 'is'),
('called', 'called'),
('ueather', 'Heather'),
('.', '.')]
Model Information
| Model Name: | check_spelling_dl |
| Type: | pipeline |
| Compatibility: | Spark NLP 2.7.5+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
Included Models
SentenceDetectorDLModel
ContextSpellCheckerModel