ELECTRA Sentence 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 Copy S3 URI

How to use

...
embeddings = BertSentenceEmbeddings.pretrained("sent_electra_base_uncased", "en") \
.setInputCols("sentence") \
.setOutputCol("sentence_embeddings")
nlp_pipeline = Pipeline(stages=[document_assembler, sentence_detector, embeddings])
pipeline_model = nlp_pipeline.fit(spark.createDataFrame([[""]]).toDF("text"))
result = pipeline_model.transform(spark.createDataFrame([['I hate cancer', "Antibiotics aren't painkiller"]], ["text"]))
...
val embeddings = BertSentenceEmbeddings.pretrained("sent_electra_base_uncased", "en")
.setInputCols("sentence")
.setOutputCol("sentence_embeddings")
val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, embeddings))
val data = Seq("I hate cancer, "Antibiotics aren't painkiller").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu

text = ["I hate cancer", "Antibiotics aren't painkiller"]
embeddings_df = nlu.load('en.embed_sentence.electra_base_uncased').predict(text, output_level='sentence')
embeddings_df

Results

	sentence	                        en_embed_sentence_electra_base_uncased_embeddings
		
I hate cancer 	                  [0.18555310368537903, -0.1990899294614792, 0.2...
Antibiotics aren't painkiller 	[-0.23764970898628235, -0.21351191401481628, -...

Model Information

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

Data Source

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