Methods › Natural Language Processing › Language Models › ProphetNet

ProphetNet

11 papers tagged archive 2025-07-28

Introduced by Weizhen Qi et al. in ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

ProphetNet is a sequence-to-sequence pre-training model that 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 further help predict multiple future tokens.

PaperSource

Papers archive 2025-07-28

11 shown of 11, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

18 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Text Summarization5
Abstractive Text Summarization4
Question Generation4
Question-Generation4
Prediction3
Text Generation2
Articles1
Code Generation1
Event-Driven Trading1
Extractive Summarization1
Future prediction1
Natural Language Understanding1
Open-Domain Dialog1
Survey1
Text Simplification1
Time Series Analysis1
Transfer Learning1
Translation1

Usage over time archive 2025-07-28

Papers per year tagged with ProphetNet: 2020 to 2024, peak 4 4 0 2020: 4 papers 2020 2021: 2 papers 2021 2022: 1 paper 2022 2023: 1 paper 2023 2024: 3 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (11 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Language ModelsTransformers

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