ALBERT Embeddings (Large Uncase)

Description

ALBERT is “A Lite” version of BERT, a popular unsupervised language representation learning algorithm. ALBERT uses parameter-reduction techniques that allow for large-scale configurations, overcome previous memory limitations, and achieve better behavior with respect to model degradation. The details are described in the paper “ALBERT: A Lite BERT for Self-supervised Learning of Language Representations.”

Live Demo Open in Colab Download Copy S3 URI

How to use

...
embeddings = AlbertEmbeddings.pretrained("albert_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 = AlbertEmbeddings.pretrained("albert_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.albert.large_uncased').predict(text, output_level='token')
embeddings_df

Results

	token	en_embed_albert_large_uncased_embeddings
	
	I	[0.3967159688472748, -0.6448764801025391, -0.3...
	love	[1.1107065677642822, -0.2454298734664917, 0.60...
	NLP	[0.02937467396259308, -0.7092287540435791, -0....

Model Information

Data Source

The model is imported from https://tfhub.dev/google/albert_large/3