ELECTRA Embeddings(ELECTRA Base)

Description

ELECTRA is a BERT-like model that is pre-trained as a discriminator in a set-up resembling a generative adversarial network (GAN). It was originally published by: Kevin Clark and Minh-Thang Luong and Quoc V. Le and Christopher D. Manning: ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators, ICLR 2020.

Live Demo Open in Colab Download Copy S3 URI

How to use

...
embeddings = BertEmbeddings.pretrained("electra_base_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("electra_base_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.electra.base_uncased').predict(text, output_level='token')
embeddings_df

Results

	token	en_embed_electra_base_uncased_embeddings
		
	I 	[-0.5244714021682739, -0.0994749441742897, 0.2...
love 	[-0.14990234375, -0.45483139157295227, 0.28477...
NLP 	[-0.030217083171010017, -0.43060103058815, -0....

Model Information

Data Source

The model is imported from https://tfhub.dev/google/electra_base/2