{"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/multi-news-a-large-scale-multi-document","title":"Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model","arxiv_id":"1906.01749","date":"2019-06-04","proceeding":"ACL 2019 7","authors":["Alexander R. Fabbri","Irene Li","Tianwei She","Suyi Li","Dragomir R. Radev"],"abstract":"Automatic generation of summaries from multiple news articles is a valuable tool as the number of online publications grows rapidly. Single document summarization (SDS) systems have benefited from advances in neural encoder-decoder model thanks to the availability of large datasets. However, multi-document summarization (MDS) of news articles has been limited to datasets of a couple of hundred examples. In this paper, we introduce Multi-News, the first large-scale MDS news dataset. Additionally, we propose an end-to-end model which incorporates a traditional extractive summarization model with a standard SDS model and achieves competitive results on MDS datasets. We benchmark several methods on Multi-News and release our data and code in hope that this work will promote advances in summarization in the multi-document setting.","url_abs":"https://arxiv.org/abs/1906.01749v3","url_pdf":"https://arxiv.org/pdf/1906.01749v3.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":"multi-news-a-large-scale-multi-document","repo_url":"https://github.com/Alex-Fabbri/Multi-News","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"extractive-summarization","task_name":"Extractive Summarization"},{"task_slug":"multi-document-summarization","task_name":"Multi-Document Summarization"}],"methods":[],"datasets_introduced":[{"slug":"multi-news","name":"Multi-News","full_name":"Multi-News"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-document-summarization-on-multi-news","task":"Multi-Document Summarization","dataset":"Multi-News","model":"Hi-MAP","rank_in_archive_order":5,"of":6,"metrics":{"ROUGE-1":"43.47","ROUGE-2":"14.89","ROUGE-SU4":"17.41"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.01749","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}