Description
BERT Model with sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for multi-class document classification tasks.
bert_multilingual_sequence_classifier_allocine is a fine-tuned BERT model that is ready to be used for Sequence Classification tasks such as sentiment analysis or multi-class text classification and it achieves state-of-the-art performance.
We used TFBertForSequenceClassification to train this model and used BertForSequenceClassification annotator in Spark NLP 🚀 for prediction at scale!
Predicted Entities
neg, pos
How to use
document_assembler = DocumentAssembler() \
.setInputCol('text') \
.setOutputCol('document')
tokenizer = Tokenizer() \
.setInputCols(['document']) \
.setOutputCol('token')
sequenceClassifier = BertForSequenceClassification \
.pretrained('bert_multilingual_sequence_classifier_allocine', 'fr') \
.setInputCols(['token', 'document']) \
.setOutputCol('class') \
.setCaseSensitive(True) \
.setMaxSentenceLength(512)
pipeline = Pipeline(stages=[
document_assembler,
tokenizer,
sequenceClassifier
])
example = spark.createDataFrame([['j'ai bien aime le film harry potter!']]).toDF("text")
result = pipeline.fit(example).transform(example)
val document_assembler = DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = Tokenizer()
.setInputCols("document")
.setOutputCol("token")
val tokenClassifier = BertForSequenceClassification.pretrained("bert_multilingual_sequence_classifier_allocine", "fr")
.setInputCols("document", "token")
.setOutputCol("class")
.setCaseSensitive(true)
.setMaxSentenceLength(512)
val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, sequenceClassifier))
val example = Seq("j'ai bien aime le film harry potter!").toDS.toDF("text")
val result = pipeline.fit(example).transform(example)
import nlu
nlu.load("fr.classify.bert.multilingual").predict("""Put your text here.""")
Results
* +--------------------+
* |result |
* +--------------------+
* |[neg, neg] |
* |[pos, pos, pos, pos]|
* +--------------------+
Model Information
| Model Name: | bert_multilingual_sequence_classifier_allocine |
| Compatibility: | Spark NLP 3.3.2+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [token, document] |
| Output Labels: | [class] |
| Language: | fr |
| Case sensitive: | true |
| Max sentense length: | 512 |
Data Source
https://huggingface.co/datasets/allocine
Benchmarking
precision recall f1-score support
neg 0.95 0.96 0.96 10294
pos 0.96 0.95 0.95 9706
accuracy 0.95 20000
macro avg 0.95 0.95 0.95 20000
weighted avg 0.95 0.95 0.95 20000