{"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/duplex-sequence-to-sequence-learning-for","title":"Duplex Sequence-to-Sequence Learning for Reversible Machine Translation","arxiv_id":"2105.03458","date":"2021-05-07","proceeding":"NeurIPS 2021 12","authors":["Zaixiang Zheng","Hao Zhou","ShuJian Huang","Jiajun Chen","Jingjing Xu","Lei LI"],"abstract":"Sequence-to-sequence learning naturally has two directions. How to effectively utilize supervision signals from both directions? Existing approaches either require two separate models, or a multitask-learned model but with inferior performance. In this paper, we propose REDER (Reversible Duplex Transformer), a parameter-efficient model and apply it to machine translation. Either end of REDER can simultaneously input and output a distinct language. Thus REDER enables reversible machine translation by simply flipping the input and output ends. Experiments verify that REDER achieves the first success of reversible machine translation, which helps outperform its multitask-trained baselines by up to 1.3 BLEU.","url_abs":"https://arxiv.org/abs/2105.03458v2","url_pdf":"https://arxiv.org/pdf/2105.03458v2.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":"duplex-sequence-to-sequence-learning-for","repo_url":"https://github.com/zhengzx-nlp/reder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.03458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03458"}},"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":"deterministic:regex_extraction","url":"https://github.com/zhengzx-nlp/REDER","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhengzx-nlp/reder","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"82bdf940665aeeb4","entry":"safe_readline","repo":"zhengzx-nlp/REDER","repo_kind":"official","path":"fairseq/binarizer.py","file_url":"https://github.com/zhengzx-nlp/REDER/blob/HEAD/fairseq/binarizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"82bdf940665aeeb4"}},{"code_sha256_prefix":"ca277f5f746f599a","entry":"convert_mask_to_lengths","repo":"zhengzx-nlp/REDER","repo_kind":"official","path":"nonauto/models/REDER/model_utils.py","file_url":"https://github.com/zhengzx-nlp/REDER/blob/HEAD/nonauto/models/REDER/model_utils.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":false,"mcp_get_code":{"code_sha256":"ca277f5f746f599a"}},{"code_sha256_prefix":"666286d34456fe05","entry":"tensor_mean_by_mask","repo":"zhengzx-nlp/REDER","repo_kind":"official","path":"nonauto/models/REDER/model_utils.py","file_url":"https://github.com/zhengzx-nlp/REDER/blob/HEAD/nonauto/models/REDER/model_utils.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":false,"mcp_get_code":{"code_sha256":"666286d34456fe05"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}