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.

Download

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(pd.DataFrame({"text": ["I love NLP"]})))
...
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 result = pipeline.fit(Seq.empty["I love NLP"].toDS.toDF("text")).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

Model Name: electra_base_uncased
Type: embeddings
Compatibility: Spark NLP 2.6.0+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [word_embeddings]
Language: [en]
Dimension: 768
Case sensitive: false

Data Source

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