Abstractive Summarization by BART - DistilBART XSUM

Description

“BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension Transformer” The Facebook BART (Bidirectional and Auto-Regressive Transformer) model is a state-of-the-art language generation model that was introduced by Facebook AI in 2019. It is based on the transformer architecture and is designed to handle a wide range of natural language processing tasks such as text generation, summarization, and machine translation.

This pre-trained model is DistilBART fine-tuned on the Extreme Summarization (XSum) Dataset.

Predicted Entities

Live Demo Open in Colab Download Copy S3 URI

How to use

bart = BartTransformer.pretrained("distilbart_xsum_12_6") \
            .setTask("summarize:") \
            .setMaxOutputLength(200) \
            .setInputCols(["documents"]) \
            .setOutputCol("summaries")

val bart = BartTransformer.pretrained("distilbart_xsum_12_6")
            .setTask("summarize:")
            .setMaxOutputLength(200)
            .setInputCols("documents")
            .setOutputCol("summaries")

Model Information

References

https://huggingface.co/sshleifer/distilbart-xsum-12-6