Italian T5ForConditionalGeneration Small Cased model (from it5)

Description

Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. it5-efficient-small-el32-news-summarization is a Italian model originally trained by it5.

Live Demo Open in Colab Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
    .setInputCols("text") \
    .setOutputCols("document")

t5 = T5Transformer.pretrained("t5_it5_efficient_small_el32_news_summarization","it") \
    .setInputCols("document") \
    .setOutputCol("answers")
    
pipeline = Pipeline(stages=[documentAssembler, t5])

data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")

result = pipeline.fit(data).transform(data)

val documentAssembler = new DocumentAssembler() 
      .setInputCols("text")
      .setOutputCols("document")
       
val t5 = T5Transformer.pretrained("t5_it5_efficient_small_el32_news_summarization","it") 
    .setInputCols("document")
    .setOutputCol("answers")
   
val pipeline = new Pipeline().setStages(Array(documentAssembler, t5))

val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text")

val result = pipeline.fit(data).transform(data)

Model Information

References

• https://huggingface.co/it5/it5-efficient-small-el32-news-summarization
• https://github.com/stefan-it
• https://arxiv.org/abs/2203.03759
• https://gsarti.com
• https://malvinanissim.github.io
• https://arxiv.org/abs/2109.10686
• https://github.com/gsarti/it5
• https://paperswithcode.com/sota?task=News+Summarization&dataset=NewsSum-IT