{"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-training-via-paraphrasing","title":"Pre-training via Paraphrasing","arxiv_id":"2006.15020","date":"2020-06-26","proceeding":"NeurIPS 2020 12","authors":["Mike Lewis","Marjan Ghazvininejad","Gargi Ghosh","Armen Aghajanyan","Sida Wang","Luke Zettlemoyer"],"abstract":"We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual multi-document paraphrasing objective. MARGE provides an alternative to the dominant masked language modeling paradigm, where we self-supervise the reconstruction of target text by retrieving a set of related texts (in many languages) and conditioning on them to maximize the likelihood of generating the original. We show it is possible to jointly learn to do retrieval and reconstruction, given only a random initialization. The objective noisily captures aspects of paraphrase, translation, multi-document summarization, and information retrieval, allowing for strong zero-shot performance on several tasks. For example, with no additional task-specific training we achieve BLEU scores of up to 35.8 for document translation. We further show that fine-tuning gives strong performance on a range of discriminative and generative tasks in many languages, making MARGE the most generally applicable pre-training method to date.","url_abs":"https://arxiv.org/abs/2006.15020v1","url_pdf":"https://arxiv.org/pdf/2006.15020v1.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-training-via-paraphrasing","repo_url":"https://github.com/Zefty/rag-end2end-retriever","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"pre-training-via-paraphrasing","repo_url":"https://github.com/lucidrains/marge-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"document-translation","task_name":"Document Translation"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"multi-document-summarization","task_name":"Multi-Document Summarization"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.15020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15020"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Zefty/rag-end2end-retriever","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/marge-pytorch","reach":null}],"summary":{"ran":7,"ran_violates":2,"ran_honours":3,"ran_fixture":1,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"listed":{"samples":15,"ran":12,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"a23d31dcc7838ddb","entry":"AutoregressiveWrapper","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a23d31dcc7838ddb"}},{"code_sha256_prefix":"fb7817bba2fe0a0b","entry":"CrossAttention","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb7817bba2fe0a0b"}},{"code_sha256_prefix":"2f5068b67b6e8ba9","entry":"FeedForward","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f5068b67b6e8ba9"}},{"code_sha256_prefix":"5f34e2fdaf110b16","entry":"GEGLU","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f34e2fdaf110b16"}},{"code_sha256_prefix":"91253a4da85ebfde","entry":"PreNorm","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91253a4da85ebfde"}},{"code_sha256_prefix":"2420acac5ce29a6d","entry":"SelfAttention","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2420acac5ce29a6d"}},{"code_sha256_prefix":"85f155dff8d3e5f1","entry":"TransformerWrapper","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85f155dff8d3e5f1"}},{"code_sha256_prefix":"d1003e60be6533a9","entry":"default","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"d1003e60be6533a9"}},{"code_sha256_prefix":"00cc1741a5867494","entry":"default","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/autoregressive_wrapper.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/autoregressive_wrapper.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00cc1741a5867494"}},{"code_sha256_prefix":"b2cc37d9d1652bf0","entry":"distill_attn_loss","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2cc37d9d1652bf0"}},{"code_sha256_prefix":"608e364a9d2376a3","entry":"exists","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"608e364a9d2376a3"}},{"code_sha256_prefix":"caeb28d34b34bc2a","entry":"identity","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"caeb28d34b34bc2a"}},{"code_sha256_prefix":"6269424d608eba34","entry":"log","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/autoregressive_wrapper.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/autoregressive_wrapper.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6269424d608eba34"}},{"code_sha256_prefix":"3b65d5d77510c964","entry":"top_k","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b65d5d77510c964"}},{"code_sha256_prefix":"6061c7c2f893c5a4","entry":"top_p","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/autoregressive_wrapper.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/autoregressive_wrapper.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6061c7c2f893c5a4"}},{"code_sha256_prefix":"94e14679f0392a49","entry":"Decoder","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94e14679f0392a49"}},{"code_sha256_prefix":"2d3108123a370798","entry":"Encoder","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d3108123a370798"}},{"code_sha256_prefix":"8cd72863751d5967","entry":"Marge","repo":"lucidrains/marge-pytorch","repo_kind":"listed","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8cd72863751d5967"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}