Description
This model was imported from Hugging Face and it’s been fine-tuned on emotion dataset, leveraging Bert embeddings and BertForSequenceClassification for text classification purposes.
Predicted Entities
sadness, joy, love, anger, fear, surprise
How to use
document_assembler = DocumentAssembler() \
.setInputCol('text') \
.setOutputCol('document')
tokenizer = Tokenizer() \
.setInputCols(['document']) \
.setOutputCol('token')
sequenceClassifier = BertForSequenceClassification \
.pretrained('bert_sequence_classifier_emotion', 'en') \
.setInputCols(['token', 'document']) \
.setOutputCol('class')
pipeline = Pipeline(stages=[document_assembler, tokenizer, sequenceClassifier])
example = spark.createDataFrame([["What do you mean? Are you kidding me?"]]).toDF("text")
result = pipeline.fit(example).transform(example)
val document_assembler = DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = Tokenizer()
.setInputCols(Array("document"))
.setOutputCol("token")
val tokenClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_emotion", "en")
.setInputCols(Array("document", "token"))
.setOutputCol("class")
val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, sequenceClassifier))
val example = Seq.empty["What do you mean? Are you kidding me?"].toDS.toDF("text")
val result = pipeline.fit(example).transform(example)
import nlu
nlu.load("en.classify.emotion.bert").predict("""What do you mean? Are you kidding me?""")
Results
['anger']
Model Information
| Model Name: | bert_sequence_classifier_emotion |
| Compatibility: | Spark NLP 3.3.4+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [class] |
| Language: | en |
| Size: | 410.1 MB |
| Case sensitive: | true |
| Max sentence length: | 128 |
Data Source
https://huggingface.co/datasets/viewer/?dataset=emotion
Benchmarking
NOTE: The author didn’t share Precision / Recall / F1, only Validation Accuracy was shared as Evaluation Results.
Validation Accuracy: 0.931