Description
Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. electricidad-base-finetuned-sst2-es is a Spanish model originally trained by mrm8488.
Predicted Entities
NEG, NEU, POS
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")
classifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_electricidad_base_finetuned_sst2","es") .setInputCols(["document", "token"]) .setOutputCol("class")
pipeline = Pipeline(stages=[documentAssembler, tokenizer, classifier])
data = spark.createDataFrame([["I love Spark NLP"]]).toDF("text")
result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = new Tokenizer()
.setInputCols(Array("document"))
.setOutputCol("token")
val classifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_electricidad_base_finetuned_sst2","es")
.setInputCols(Array("document", "token"))
.setOutputCol("embeddings")
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, classifier))
val data = Seq("I love Spark NLP").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.classify.bert.base_finetuned").predict("""I love Spark NLP""")
Model Information
| Model Name: | bert_sequence_classifier_electricidad_base_finetuned_sst2 |
| Compatibility: | Spark NLP 4.1.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [class] |
| Language: | en |
| Size: | 412.4 MB |
| Case sensitive: | true |
| Max sentence length: | 128 |
References
https://huggingface.co/mrm8488/electricidad-base-finetuned-sst2-es