ELECTRA Embeddings(ELECTRA Small)

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_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("electra_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.electra.large_uncased').predict(text, output_level='token')
embeddings_df

Results

	en_embed_electra_large_uncased_embeddings	            token
		
	[0.1289837807416916, -0.18811583518981934, 0.0... 	I
[-0.02723774127662182, 0.0757141262292862, 0.3... 	love
[0.4146347939968109, -0.31447598338127136, -0.... 	NLP

Model Information

Data Source

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