Description
This model was imported from Hugging Face (link) and it’s been trained on a Icelandic synthetic data to detect typos, leveraging DistilBERT embeddings and DistilBertForTokenClassification for NER purposes. It classifies typo tokens as PO.
Predicted Entities
PO
How to use
documentAssembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentenceDetector = SentenceDetector()\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = Tokenizer()\
.setInputCols(["sentence"])\
.setOutputCol("token")
tokenClassifier = DistilBertForTokenClassification.pretrained("distilbert_token_classifier_typo_detector", "is")\
.setInputCols(["sentence",'token'])\
.setOutputCol("ner")
ner_converter = NerConverter()\
.setInputCols(["sentence", "token", "ner"])\
.setOutputCol("ner_chunk")
nlpPipeline = Pipeline(stages=[documentAssembler, sentenceDetector, tokenizer, tokenClassifier, ner_converter])
text = """Það er miög auðvelt að draga marktækar álykanir af texta með Spark NLP."""
data = spark.createDataFrame([[text]]).toDF("text")
result = nlpPipeline.fit(data).transform(data)
val documentAssembler = DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentenceDetector = SentenceDetector()
.setInputCols(Array("document"))
.setOutputCol("sentence")
val tokenizer = Tokenizer()
.setInputCols(Array("sentence"))
.setOutputCol("token")
val tokenClassifier = DistilBertForTokenClassification.pretrained("distilbert_token_classifier_typo_detector", "is")
.setInputCols(Array("sentence","token"))
.setOutputCol("ner")
val ner_converter = NerConverter()
.setInputCols(Array("sentence", "token", "ner"))
.setOutputCol("ner_chunk")
val pipeline = new Pipeline().setStages(Array(documentAssembler, sentenceDetector, tokenizer, tokenClassifier, ner_converter))
val example = Seq.empty["Það er miög auðvelt að draga marktækar álykanir af texta með Spark NLP."].toDS.toDF("text")
val result = pipeline.fit(example).transform(example)
import nlu
nlu.load("is.ner.distil_bert").predict("""Það er miög auðvelt að draga marktækar álykanir af texta með Spark NLP.""")
Results
+--------+---------+
|chunk |ner_label|
+--------+---------+
|miög |PO |
|álykanir|PO |
+--------+---------+
Model Information
| Model Name: | distilbert_token_classifier_typo_detector |
| Compatibility: | Spark NLP 3.3.4+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [ner] |
| Language: | is |
| Size: | 505.7 MB |
| Case sensitive: | true |
| Max sentence length: | 256 |
Benchmarking
label precision recall f1-score support
micro avg 0.98954 0.967603 0.978448 43800.0
macro-avg 0.98954 0.967603 0.978448 43800.0
weighted-avg 0.98954 0.967603 0.978448 43800.0