Description
Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-base-styleclassification-subjective-neutral
is a English model originally trained by cffl
.
Predicted Entities
NEUTRAL
, SUBJECTIVE
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")
sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_base_styleclassification_subjective_neutral","en") \
.setInputCols(["document", "token"]) \
.setOutputCol("class")
pipeline = Pipeline(stages=[documentAssembler, tokenizer,sequenceClassifier_loaded])
data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).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 sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_base_styleclassification_subjective_neutral","en")
.setInputCols(Array("document", "token"))
.setOutputCol("class")
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer,sequenceClassifier_loaded))
val data = Seq("PUT YOUR STRING HERE").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.classify.bert.base.by_cffl").predict("""PUT YOUR STRING HERE""")
Model Information
Model Name: | bert_classifier_base_styleclassification_subjective_neutral |
Compatibility: | Spark NLP 4.2.0+ |
License: | Open Source |
Edition: | Official |
Input Labels: | [document, token] |
Output Labels: | [class] |
Language: | en |
Size: | 410.0 MB |
Case sensitive: | true |
Max sentence length: | 256 |
References
- https://huggingface.co/cffl/bert-base-styleclassification-subjective-neutral
- https://arxiv.org/pdf/1911.09709.pdf
- https://arxiv.org/pdf/1703.01365.pdf
- https://github.com/openai/gpt-2/blob/master/model_card.md#out-of-scope-use-cases
- https://github.com/fastforwardlabs/text-style-transfer/blob/main/scripts/train/classifier/train_classifier.py
- https://github.com/fastforwardlabs/text-style-transfer/blob/main/notebooks/WNC_full_style_classifier_evaluation.ipynb