Smaller BERT Embeddings (L-12_H-768_A-12)

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.

Live Demo Open in Colab Download Copy S3 URI

How to use

...
embeddings = BertEmbeddings.pretrained("small_bert_L12_768", "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("small_bert_L12_768", "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.small_L12_768').predict(text, output_level='token')
embeddings_df

Results

	token	en_embed_bert_small_L12_768_embeddings
		
	I 	[0.2770369052886963, 0.460345059633255, -0.236...
love 	[-0.19471393525600433, 0.05537150800228119, -0...
NLP 	[0.06311562657356262, 0.18206995725631714, -0....

Model Information

Data Source

The model is imported from https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-12_H-768_A-12/1