Description
This model contains a deep bidirectional transformer trained on Wikipedia and the BookCorpus. The details are described in the paper “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding”.
How to use
...
embeddings = BertSentenceEmbeddings.pretrained("sent_bert_large_uncased", "en") \
.setInputCols("sentence") \
.setOutputCol("sentence_embeddings")
nlp_pipeline = Pipeline(stages=[document_assembler, sentence_detector, embeddings])
pipeline_model = nlp_pipeline.fit(spark.createDataFrame([[""]]).toDF("text"))
result = pipeline_model.transform(spark.createDataFrame([['I hate cancer', "Antibiotics aren't painkiller"]], ["text"]))
...
val embeddings = BertSentenceEmbeddings.pretrained("sent_bert_large_uncased", "en")
.setInputCols("sentence")
.setOutputCol("sentence_embeddings")
val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, embeddings))
val data = Seq("I hate cancer, "Antibiotics aren't painkiller").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
text = ["I hate cancer", "Antibiotics aren't painkiller"]
embeddings_df = nlu.load('en.embed_sentence.bert_large_uncased').predict(text, output_level='sentence')
embeddings_df
Results
sentence en_embed_sentence_bert_large_uncased_embeddings
I hate cancer [[-0.13290119171142578, -0.2996622622013092, -...
Antibiotics aren't painkiller [[-0.13290119171142578, -0.2996622622013092, -...
Model Information
| Model Name: | sent_bert_large_uncased |
| Type: | embeddings |
| Compatibility: | Spark NLP 2.6.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence] |
| Output Labels: | [sentence_embeddings] |
| Language: | [en] |
| Dimension: | 1024 |
| Case sensitive: | false |
Data Source
The model is imported from https://tfhub.dev/google/bert_uncased_L-24_H-1024_A-16/1