Papers › ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
Weizhen Qi, Yu Yan, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang, Ming Zhou
This paper presents a new sequence-to-sequence pre-training model called ProphetNet, which introduces a novel self-supervised objective named future n-gram prediction and the proposed n-stream self-attention mechanism. Instead of optimizing one-step-ahead prediction in the traditional sequence-to-sequence model, the ProphetNet is optimized by n-step ahead prediction that predicts the next n tokens simultaneously based on previous context tokens at each time step. The future n-gram prediction explicitly encourages the model to plan for the future tokens and prevent overfitting on strong local correlations. We pre-train ProphetNet using a base scale dataset (16GB) and a large-scale dataset (160GB), respectively. Then we conduct experiments on CNN/DailyMail, Gigaword, and SQuAD 1.1 benchmarks for abstractive summarization and question generation tasks. Experimental results show that ProphetNet achieves new state-of-the-art results on all these datasets compared to the models using the same scale pre-training corpus.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Abstractive Text Summarization | CNN / Daily Mail | ProphetNet | ROUGE-1 | 44.20 | #17 of 53 | Archive leaderboard | report |
| Abstractive Text Summarization | CNN / Daily Mail | ProphetNet | ROUGE-2 | 21.17 | #17 of 53 | Archive leaderboard | report |
| Abstractive Text Summarization | CNN / Daily Mail | ProphetNet | ROUGE-L | 41.30 | #17 of 53 | Archive leaderboard | report |
| Question Generation | SQuAD1.1 | ProphetNet | BLEU-4 | 23.91 | #6 of 13 | Archive leaderboard | report |
| Question Generation | SQuAD1.1 | ProphetNet | METEOR | 26.6 | #6 of 13 | Archive leaderboard | report |
| Question Generation | SQuAD1.1 | ProphetNet | ROUGE-L | 52.3 | #6 of 13 | Archive leaderboard | report |
| Text Summarization | GigaWord | ProphetNet | ROUGE-1 | 39.51 | #9 of 41 | Archive leaderboard | report |
| Text Summarization | GigaWord | ProphetNet | ROUGE-2 | 20.42 | #9 of 41 | Archive leaderboard | report |
| Text Summarization | GigaWord | ProphetNet | ROUGE-L | 36.69 | #9 of 41 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Introduced by this paper: ProphetNet
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