{"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/towards-document-level-paraphrase-generation","title":"Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering","arxiv_id":"2109.07095","date":"2021-09-15","proceeding":"Findings (EMNLP) 2021 11","authors":["Zhe Lin","Yitao Cai","Xiaojun Wan"],"abstract":"Paraphrase generation is an important task in natural language processing. Previous works focus on sentence-level paraphrase generation, while ignoring document-level paraphrase generation, which is a more challenging and valuable task. In this paper, we explore the task of document-level paraphrase generation for the first time and focus on the inter-sentence diversity by considering sentence rewriting and reordering. We propose CoRPG (Coherence Relationship guided Paraphrase Generation), which leverages graph GRU to encode the coherence relationship graph and get the coherence-aware representation for each sentence, which can be used for re-arranging the multiple (possibly modified) input sentences. We create a pseudo document-level paraphrase dataset for training CoRPG. Automatic evaluation results show CoRPG outperforms several strong baseline models on the BERTScore and diversity scores. Human evaluation also shows our model can generate document paraphrase with more diversity and semantic preservation.","url_abs":"https://arxiv.org/abs/2109.07095v1","url_pdf":"https://arxiv.org/pdf/2109.07095v1.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":"towards-document-level-paraphrase-generation","repo_url":"https://github.com/l-zhe/corpg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"paraphrase-generation","task_name":"Paraphrase Generation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-rewriting","task_name":"Sentence ReWriting"}],"methods":[{"method_slug":"gru","method_name":"GRU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.07095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07095"}},"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/l-zhe/corpg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"10865bbb99140edd","entry":"Linear","repo":"l-zhe/corpg","repo_kind":"official","path":"Transformer/Module.py","file_url":"https://github.com/l-zhe/corpg/blob/HEAD/Transformer/Module.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10865bbb99140edd"}},{"code_sha256_prefix":"3ffe1b6d87d6be57","entry":"graph_process","repo":"l-zhe/corpg","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/l-zhe/corpg/blob/HEAD/preprocess.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":"3ffe1b6d87d6be57"}},{"code_sha256_prefix":"0df2ff51a20cb4d0","entry":"key_func","repo":"l-zhe/corpg","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/l-zhe/corpg/blob/HEAD/preprocess.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":"0df2ff51a20cb4d0"}},{"code_sha256_prefix":"294f408c82f2b540","entry":"last_n_checkpoints","repo":"l-zhe/corpg","repo_kind":"official","path":"avg_param.py","file_url":"https://github.com/l-zhe/corpg/blob/HEAD/avg_param.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":"294f408c82f2b540"}},{"code_sha256_prefix":"679757044477cd58","entry":"pad_mask","repo":"l-zhe/corpg","repo_kind":"official","path":"Transformer/Module.py","file_url":"https://github.com/l-zhe/corpg/blob/HEAD/Transformer/Module.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":"679757044477cd58"}},{"code_sha256_prefix":"40eb3071da4a388b","entry":"read_file","repo":"l-zhe/corpg","repo_kind":"official","path":"eval/bleu.py","file_url":"https://github.com/l-zhe/corpg/blob/HEAD/eval/bleu.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":"40eb3071da4a388b"}},{"code_sha256_prefix":"3112bbaf3ab9dee6","entry":"triu_mask","repo":"l-zhe/corpg","repo_kind":"official","path":"Transformer/Module.py","file_url":"https://github.com/l-zhe/corpg/blob/HEAD/Transformer/Module.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":"3112bbaf3ab9dee6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}