{"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/efficient-attentions-for-long-document","title":"Efficient Attentions for Long Document Summarization","arxiv_id":"2104.02112","date":"2021-04-05","proceeding":"NAACL 2021 4","authors":["Luyang Huang","Shuyang Cao","Nikolaus Parulian","Heng Ji","Lu Wang"],"abstract":"The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization. In this paper, we propose Hepos, a novel efficient encoder-decoder attention with head-wise positional strides to effectively pinpoint salient information from the source. We further conduct a systematic study of existing efficient self-attentions. Combined with Hepos, we are able to process ten times more tokens than existing models that use full attentions. For evaluation, we present a new dataset, GovReport, with significantly longer documents and summaries. Results show that our models produce significantly higher ROUGE scores than competitive comparisons, including new state-of-the-art results on PubMed. Human evaluation also shows that our models generate more informative summaries with fewer unfaithful errors.","url_abs":"https://arxiv.org/abs/2104.02112v2","url_pdf":"https://arxiv.org/pdf/2104.02112v2.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":"efficient-attentions-for-long-document","repo_url":"https://github.com/luyang-huang96/LongDocSum","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"document-summarization","task_name":"Document Summarization"}],"methods":[],"datasets_introduced":[{"slug":"govreport","name":"GovReport","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.02112","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}