Multilingual T5ForConditionalGeneration Base Cased model (from sonoisa)

Description

Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. t5-base-english-japanese is a Multilingual model originally trained by sonoisa.

Live Demo Open in Colab Download Copy S3 URI

How to use

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

t5 = T5Transformer.pretrained("t5_base_english_japanese","xx") \
    .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_base_english_japanese","xx") 
    .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/sonoisa/t5-base-english-japanese
• https://en.wikipedia.org
• https://ja.wikipedia.org
• https://oscar-corpus.com
• http://data.statmt.org/cc-100/
• http://data.statmt.org/cc-100/
• https://github.com/sonoisa/t5-japanese
• https://creativecommons.org/licenses/by-sa/4.0/deed.ja
• http://commoncrawl.org/terms-of-use/