Smaller BERT Sentence Embeddings (L-12_H-256_A-4)

Description

This is one of the smaller BERT models referenced in Well-Read Students Learn Better: On the Importance of Pre-training Compact Models. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher.

Download

How to use

...
embeddings = BertEmbeddings.pretrained("sent_small_bert_L12_256", "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(pd.DataFrame({"text": ["I hate cancer, "Antibiotics aren't painkiller"]})))
...
val embeddings = BertEmbeddings.pretrained("sent_small_bert_L12_256", "en")
      .setInputCols("sentence")
      .setOutputCol("sentence_embeddings")
val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, embeddings))
val result = pipeline.fit(Seq.empty["I hate cancer, "Antibiotics aren't painkiller"].toDS.toDF("text")).transform(data)
import nlu

text = ["I hate cancer", "Antibiotics aren't painkiller"]
embeddings_df = nlu.load('en.embed_sentence.small_bert_L12_256').predict(text, output_level='sentence')
embeddings_df

Results

	sentence	                        en_embed_sentence_small_bert_L12_256_embeddings

 	I hate cancer 	                  [0.9404042959213257, -0.5918057560920715, 0.07...
 	Antibiotics aren't painkiller 	[0.1526544690132141, 0.050494179129600525, -0....

Model Information

Model Name: sent_small_bert_L12_256
Type: embeddings
Compatibility: Spark NLP 2.6.0+
License: Open Source
Edition: Official
Input Labels: [sentence]
Output Labels: [sentence_embeddings]
Language: [en]
Dimension: 256
Case sensitive: false

Data Source

The model is imported from https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-12_H-256_A-4/1