flâneur — a map of the web's best reading

Introducing BART | TensorGoose

sshleifer.github.io · 2,479 words · saved by 1 readers

Episode 1 – a mysterious new Seq2Seq model with state of the art summarization performance visits a popular open source library

Overview Background: Seq2Seq Pretraining Bert vs. GPT2 Encoder-Decoder Pretraining: Fill In the Span Summarization Demo: BartForConditionalGeneration Conclusion Overview For the past few weeks, I worked on integrating BART into transformers . This post covers the high-level differences between BART and its predecessors and how to use the new BartForConditionalGeneration to summarize documents. Leave a comment below if you have any questions! Background: Seq2Seq Pretraining In October 2019, teams from Google and Facebook published new transformer papers: T5 and BART . Both papers achieved bette

Explore this link on the map →

related reading