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 = BertEmbeddings.pretrained("bert_large_uncased", "en") \
.setInputCols("sentence", "token") \
.setOutputCol("embeddings")
nlp_pipeline = Pipeline(stages=[document_assembler, sentence_detector, tokenizer, embeddings])
pipeline_model = nlp_pipeline.fit(spark.createDataFrame([[""]]).toDF("text"))
result = pipeline_model.transform(spark.createDataFrame([['I love NLP']], ["text"]))
...
val embeddings = BertEmbeddings.pretrained("bert_large_uncased", "en")
.setInputCols("sentence", "token")
.setOutputCol("embeddings")
val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, tokenizer, embeddings))
val data = Seq("I love NLP").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
text = ["I love NLP"]
embeddings_df = nlu.load('en.embed.bert.large_uncased').predict(text, output_level='token')
embeddings_df
Results
en_embed_bert_large_uncased_embeddings token
[-0.07447264343500137, -0.337308406829834, -0.... I
[-0.5735481977462769, -0.3580206632614136, -0.... love
[-0.3929762840270996, -0.4147087037563324, 0.2... NLP
Model Information
| Model Name: | bert_large_uncased |
| Type: | embeddings |
| Compatibility: | Spark NLP 2.6.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [word_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