{"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/docmt5-document-level-pretraining-of","title":"DOCmT5: Document-Level Pretraining of Multilingual Language Models","arxiv_id":"2112.08709","date":"2021-12-16","proceeding":"Findings (NAACL) 2022 7","authors":["Chia-Hsuan Lee","Aditya Siddhant","Viresh Ratnakar","Melvin Johnson"],"abstract":"In this paper, we introduce DOCmT5, a multilingual sequence-to-sequence language model pretrained with large scale parallel documents. While previous approaches have focused on leveraging sentence-level parallel data, we try to build a general-purpose pretrained model that can understand and generate long documents. We propose a simple and effective pretraining objective - Document reordering Machine Translation (DrMT), in which the input documents that are shuffled and masked need to be translated. DrMT brings consistent improvements over strong baselines on a variety of document-level generation tasks, including over 12 BLEU points for seen-language-pair document-level MT, over 7 BLEU points for unseen-language-pair document-level MT and over 3 ROUGE-1 points for seen-language-pair cross-lingual summarization. We achieve state-of-the-art (SOTA) on WMT20 De-En and IWSLT15 Zh-En document translation tasks. We also conduct extensive analysis on various factors for document pretraining, including (1) The effects of pretraining data quality and (2) The effects of combining mono-lingual and cross-lingual pretraining. We plan to make our model checkpoints publicly available.","url_abs":"https://arxiv.org/abs/2112.08709v2","url_pdf":"https://arxiv.org/pdf/2112.08709v2.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":[],"tasks":[{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"document-translation","task_name":"Document Translation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"de-en","task_name":"de-en"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-summarization-on-wikilingua-tr-en","task":"Document Summarization","dataset":"WikiLingua (tr->en)","model":"DOCmT5","rank_in_archive_order":1,"of":1,"metrics":{"Rouge-L":"31.37"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.08709","atlas_url":"https://app.syntology.ai/?focus=2112.08709","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}