BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

I confused this with BERT lol

The encoder is similar to BERT; the decoder is similar to GPT.

Citation

(Lewis et al., 2019)

Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019). BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. https://arxiv.org/pdf/1910.13461