{"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/pre-trained-language-model-representations","title":"Pre-trained Language Model Representations for Language Generation","arxiv_id":"1903.09722","date":"2019-03-22","proceeding":"NAACL 2019 6","authors":["Sergey Edunov","Alexei Baevski","Michael Auli"],"abstract":"Pre-trained language model representations have been successful in a wide\nrange of language understanding tasks. In this paper, we examine different\nstrategies to integrate pre-trained representations into sequence to sequence\nmodels and apply it to neural machine translation and abstractive\nsummarization. We find that pre-trained representations are most effective when\nadded to the encoder network which slows inference by only 14%. Our experiments\nin machine translation show gains of up to 5.3 BLEU in a simulated\nresource-poor setup. While returns diminish with more labeled data, we still\nobserve improvements when millions of sentence-pairs are available. Finally, on\nabstractive summarization we achieve a new state of the art on the full text\nversion of CNN/DailyMail.","url_abs":"http://arxiv.org/abs/1903.09722v2","url_pdf":"http://arxiv.org/pdf/1903.09722v2.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":"pre-trained-language-model-representations","repo_url":"https://github.com/pytorch/fairseq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"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":"text-generation","task_name":"Text Generation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.09722","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}