{"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/stacl-simultaneous-translation-with","title":"STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework","arxiv_id":"1810.08398","date":"2018-10-19","proceeding":"ACL 2019 7","authors":["Mingbo Ma","Liang Huang","Hao Xiong","Renjie Zheng","Kaibo Liu","Baigong Zheng","Chuanqiang Zhang","Zhongjun He","Hairong Liu","Xing Li","Hua Wu","Haifeng Wang"],"abstract":"Simultaneous translation, which translates sentences before they are finished, is useful in many scenarios but is notoriously difficult due to word-order differences. While the conventional seq-to-seq framework is only suitable for full-sentence translation, we propose a novel prefix-to-prefix framework for simultaneous translation that implicitly learns to anticipate in a single translation model. Within this framework, we present a very simple yet surprisingly effective wait-k policy trained to generate the target sentence concurrently with the source sentence, but always k words behind. Experiments show our strategy achieves low latency and reasonable quality (compared to full-sentence translation) on 4 directions: zh<->en and de<->en.","url_abs":"https://arxiv.org/abs/1810.08398v5","url_pdf":"https://arxiv.org/pdf/1810.08398v5.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":"stacl-simultaneous-translation-with","repo_url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/simultaneous_translation/stacl","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"stacl-simultaneous-translation-with","repo_url":"https://github.com/SimulTrans-demo/STACL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"stacl-simultaneous-translation-with","repo_url":"https://github.com/autosimtrans/SimulTransBaseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"de-en","task_name":"de-en"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.08398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.08398"}},"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/PaddlePaddle/PaddleNLP/tree/develop/examples/simultaneous_translation/stacl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/autosimtrans/SimulTransBaseline","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SimulTrans-demo/STACL","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":3,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":5,"ran":5,"repositories":2}},"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":5,"samples":[{"code_sha256_prefix":"1e12be0930347114","entry":"RW2AL","repo":"SimulTrans-demo/STACL","repo_kind":"listed","path":"metricAL.py","file_url":"https://github.com/SimulTrans-demo/STACL/blob/HEAD/metricAL.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1e12be0930347114"}},{"code_sha256_prefix":"cce6fead28f0af30","entry":"RW2AL_file","repo":"SimulTrans-demo/STACL","repo_kind":"listed","path":"metricAL.py","file_url":"https://github.com/SimulTrans-demo/STACL/blob/HEAD/metricAL.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cce6fead28f0af30"}},{"code_sha256_prefix":"b1f4c7e40dfb8b33","entry":"RW2AP","repo":"SimulTrans-demo/STACL","repo_kind":"listed","path":"metricAL.py","file_url":"https://github.com/SimulTrans-demo/STACL/blob/HEAD/metricAL.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1f4c7e40dfb8b33"}},{"code_sha256_prefix":"1492225d0a37a248","entry":"position_encoding_init","repo":"autosimtrans/SimulTransBaseline","repo_kind":"listed","path":"model.py","file_url":"https://github.com/autosimtrans/SimulTransBaseline/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1492225d0a37a248"}},{"code_sha256_prefix":"e85b5e345fefc0d0","entry":"post_process_seq","repo":"autosimtrans/SimulTransBaseline","repo_kind":"listed","path":"predict.py","file_url":"https://github.com/autosimtrans/SimulTransBaseline/blob/HEAD/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e85b5e345fefc0d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}