Encoder–Decoders · 2020

BART: Denoising Seq2Seq Pre-training

Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, Luke Zettlemoyer

BART pretrains a full encoder-decoder Transformer as a denoising autoencoder that reconstructs original text from arbitrarily corrupted input, unifying BERT-style bidirectional encoding with GPT-style autoregressive generation for both understanding and generation tasks.

Editorial record

Plain-language summary

BART corrupts documents with noise such as token masking, deletion, sentence shuffling, and text-span infilling, then trains a bidirectional encoder plus autoregressive decoder to reconstruct the original. This seq2seq setup means the same pretrained model handles classification (via the encoder) and generation like summarization and translation (via the decoder), rather than needing separate architectures. Text infilling in particular proved effective, and BART reached strong results on generation benchmarks while remaining competitive on discriminative tasks.

Knowledge graph

Relationships

Antecedents

Descendants

Source record

Provenance

Record ID
P-021
Record created
2026-07-13
Last reviewed
2026-07-14
Record version
2

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.