{"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/msp-multi-stage-prompting-for-making-pre","title":"MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators","arxiv_id":"2110.06609","date":"2021-10-13","proceeding":"ACL 2022 5","authors":["Zhixing Tan","Xiangwen Zhang","Shuo Wang","Yang Liu"],"abstract":"Prompting has recently been shown as a promising approach for applying pre-trained language models to perform downstream tasks. We present Multi-Stage Prompting (MSP), a simple and automatic approach for leveraging pre-trained language models to translation tasks. To better mitigate the discrepancy between pre-training and translation, MSP divides the translation process via pre-trained language models into multiple separate stages: the encoding stage, the re-encoding stage, and the decoding stage. During each stage, we independently apply different continuous prompts for allowing pre-trained language models better shift to translation tasks. We conduct extensive experiments on three translation tasks. Experiments show that our method can significantly improve the translation performance of pre-trained language models.","url_abs":"https://arxiv.org/abs/2110.06609v2","url_pdf":"https://arxiv.org/pdf/2110.06609v2.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":"msp-multi-stage-prompting-for-making-pre","repo_url":"https://github.com/thunlp-mt/plm4mt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.06609","atlas_url":"https://app.syntology.ai/?focus=2110.06609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06609"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/thunlp-mt/plm4mt","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_draft_wrong":1,"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"bb55d10bc8ee2bfa","entry":"import_params","repo":"thunlp-mt/plm4mt","repo_kind":"official","path":"thumt/bin/trainer.py","file_url":"https://github.com/thunlp-mt/plm4mt/blob/HEAD/thumt/bin/trainer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"bb55d10bc8ee2bfa"}},{"code_sha256_prefix":"aaffde8b4d24daf4","entry":"length_to_mask","repo":"thunlp-mt/plm4mt","repo_kind":"official","path":"thumt/models/prefix.py","file_url":"https://github.com/thunlp-mt/plm4mt/blob/HEAD/thumt/models/prefix.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"aaffde8b4d24daf4"}},{"code_sha256_prefix":"e1d3da437c2d6fb3","entry":"override_params","repo":"thunlp-mt/plm4mt","repo_kind":"official","path":"thumt/bin/translator.py","file_url":"https://github.com/thunlp-mt/plm4mt/blob/HEAD/thumt/bin/translator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e1d3da437c2d6fb3"}},{"code_sha256_prefix":"256acbc162360bd6","entry":"parse_args","repo":"thunlp-mt/plm4mt","repo_kind":"official","path":"thumt/bin/trainer.py","file_url":"https://github.com/thunlp-mt/plm4mt/blob/HEAD/thumt/bin/trainer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"256acbc162360bd6"}},{"code_sha256_prefix":"da8001b0f721ab57","entry":"import_params","repo":"thunlp-mt/plm4mt","repo_kind":"official","path":"thumt/bin/translator.py","file_url":"https://github.com/thunlp-mt/plm4mt/blob/HEAD/thumt/bin/translator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"da8001b0f721ab57"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}