Description
This model is imported from Hugging Face-models. It is a BERT-Mini fine-tuned version of the age_news dataset.
Predicted Entities
World, Sports, Business, Sci/Tech
How to use
document_assembler = DocumentAssembler() \
.setInputCol('text') \
.setOutputCol('document')
tokenizer = Tokenizer() \
.setInputCols(['document']) \
.setOutputCol('token')
sequenceClassifier = BertForSequenceClassification \
.pretrained('bert_sequence_classifier_age_news', 'en') \
.setInputCols(['token', 'document']) \
.setOutputCol('class') \
.setCaseSensitive(True) \
.setMaxSentenceLength(512)
pipeline = Pipeline(stages=[document_assembler, tokenizer, sequenceClassifier])
example = spark.createDataFrame([['Microsoft has taken its first step into the metaverse.']]).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_sequence_classifier_age_news", "en")
.setInputCols("document", "token")
.setOutputCol("class")
.setCaseSensitive(true)
.setMaxSentenceLength(512)
val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, sequenceClassifier))
val example = Seq.empty["Microsoft has taken its first step into the metaverse."].toDS.toDF("text")
val result = pipeline.fit(example).transform(example)
import nlu
nlu.load("en.classify.bert.news.").predict("""Microsoft has taken its first step into the metaverse.""")
Results
['Sci/Tech']
Model Information
| Model Name: | bert_sequence_classifier_age_news |
| Compatibility: | Spark NLP 3.3.2+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [token, sentence] |
| Output Labels: | [label] |
| Language: | en |
| Case sensitive: | true |
Data Source
https://huggingface.co/mrm8488/bert-mini-finetuned-age_news-classification
Benchmarking
Test set accuracy: 0.93