Papers › Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting

Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting

2 Jan 2021EMNLP 2021 11arXiv:2101.00416archive 2025-07-28

Wangchunshu Zhou, Tao Ge, Canwen Xu, Ke Xu, Furu Wei

In this paper, we generalize text infilling (e.g., masked language models) by proposing Sequence Span Rewriting (SSR) as a self-supervised sequence-to-sequence (seq2seq) pre-training objective. SSR provides more fine-grained learning signals for text representations by supervising the model to rewrite imperfect spans to ground truth, and it is more consistent than text infilling with many downstream seq2seq tasks that rewrite a source sentences into a target sentence. Our experiments with T5 models on various seq2seq tasks show that SSR can substantially improve seq2seq pre-training. Moreover, we observe SSR is especially helpful to improve pre-training a small-size seq2seq model with a powerful imperfect span generator, which indicates a new perspective of transferring knowledge from a large model to a smaller model for seq2seq pre-training.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

michaelzhouwang/sequence_span_rewriting officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

SentenceText Infilling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdafactorAttentionAttention DropoutBPEDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLSTMLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSentencePieceSeq2SeqSigmoid ActivationSoftmaxT5Tanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections