Description
Electra model fine tuned on MeDAL, a large dataset on abbreviation disambiguation, designed for pretraining natural language understanding models in the medical domain. Check the reference here.
Predicted Entities
How to use
documentAssembler= DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentenceDetector = SentenceDetector()\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer= Tokenizer()\
.setInputCols(["sentence"])\
.setOutputCol("token")
embeddings = BertEmbeddings.pretrained("electra_medal_acronym", "en") \
.setInputCols("sentence", "token") \
.setOutputCol("embeddings")
nlpPipeline= Pipeline(stages=[documentAssembler, sentenceDetector, tokenizer, embeddings])
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentenceDetector = new SentenceDetector()
.setInputCols(Array("document"))
.setOutputCol("sentence")
val tokenizer = new Tokenizer()
.setInputCols(Array("sentence"))
.setOutputCol("token")
val embeddings = BertEmbeddings.pretrained("electra_medal_acronym", "en")
.setInputCols("sentence", "token")
.setOutputCol("embeddings")
val pipeline = new Pipeline().setStages(Array(documentAssembler, sentenceDetector, tokenizer, embeddings))
import nlu
nlu.load("en.embed.electra.medical").predict("""Put your text here.""")
Model Information
| Model Name: | electra_medal_acronym |
| Compatibility: | Spark NLP 3.3.3+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [electra] |
| Language: | en |
| Size: | 66.0 MB |
| Case sensitive: | true |
Data Source
https://github.com/BruceWen120/medal