Turkish absa_turkish_bert_based_small_pipeline pipeline BertForSequenceClassification from Sengil

Description

Pretrained BertForSequenceClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.absa_turkish_bert_based_small_pipeline is a Turkish model originally trained by Sengil.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("absa_turkish_bert_based_small_pipeline", lang = "tr")
annotations =  pipeline.transform(df)   


val pipeline = new PretrainedPipeline("absa_turkish_bert_based_small_pipeline", lang = "tr")
val annotations = pipeline.transform(df)

Model Information

Model Name: absa_turkish_bert_based_small_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: tr
Size: 414.5 MB

References

https://huggingface.co/Sengil/ABSA-Turkish-bert-based-small

Included Models

  • DocumentAssembler
  • TokenizerModel
  • BertForSequenceClassification