{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/prophetnet-predicting-future-n-gram-for-1","title":"ProphetNet: Predicting Future N-gram for Sequence-to-SequencePre-training","arxiv_id":null,"date":"2020-11-01","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Weizhen Qi","Yu Yan","Yeyun Gong","Dayiheng Liu","Nan Duan","Jiusheng Chen","Ruofei Zhang","Ming Zhou"],"abstract":"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.","url_abs":"https://aclanthology.org/2020.findings-emnlp.217","url_pdf":"https://aclanthology.org/2020.findings-emnlp.217.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"prophetnet-predicting-future-n-gram-for-1","repo_url":"https://github.com/MindCode-4/code-4/tree/main/prophetnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"prophetnet-predicting-future-n-gram-for-1","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/5/xlm_prophetnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"prophetnet-predicting-future-n-gram-for-1","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-1/prophetnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-generation","task_name":"Question-Generation"}],"methods":[{"method_slug":"prophetnet","method_name":"ProphetNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}