{"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/simulated-multiple-reference-training","title":"Simulated Multiple Reference Training Improves Low-Resource Machine Translation","arxiv_id":"2004.14524","date":"2020-04-30","proceeding":"EMNLP 2020 11","authors":["Huda Khayrallah","Brian Thompson","Matt Post","Philipp Koehn"],"abstract":"Many valid translations exist for a given sentence, yet machine translation (MT) is trained with a single reference translation, exacerbating data sparsity in low-resource settings. We introduce Simulated Multiple Reference Training (SMRT), a novel MT training method that approximates the full space of possible translations by sampling a paraphrase of the reference sentence from a paraphraser and training the MT model to predict the paraphraser's distribution over possible tokens. We demonstrate the effectiveness of SMRT in low-resource settings when translating to English, with improvements of 1.2 to 7.0 BLEU. We also find SMRT is complementary to back-translation.","url_abs":"https://arxiv.org/abs/2004.14524v2","url_pdf":"https://arxiv.org/pdf/2004.14524v2.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":"simulated-multiple-reference-training","repo_url":"https://github.com/thompsonb/fairseq-smrt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.14524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14524"}},"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/thompsonb/fairseq-smrt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"listed":{"samples":5,"ran":2,"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":5,"samples":[{"code_sha256_prefix":"90b79fe15491de83","entry":"is_master","repo":"thompsonb/fairseq-smrt","repo_kind":"listed","path":"fairseq/distributed_utils.py","file_url":"https://github.com/thompsonb/fairseq-smrt/blob/HEAD/fairseq/distributed_utils.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":"90b79fe15491de83"}},{"code_sha256_prefix":"82bdf940665aeeb4","entry":"safe_readline","repo":"thompsonb/fairseq-smrt","repo_kind":"listed","path":"fairseq/binarizer.py","file_url":"https://github.com/thompsonb/fairseq-smrt/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":"59755e76d7c3f48b","entry":"all_reduce","repo":"thompsonb/fairseq-smrt","repo_kind":"listed","path":"fairseq/distributed_utils.py","file_url":"https://github.com/thompsonb/fairseq-smrt/blob/HEAD/fairseq/distributed_utils.py","link_basis":"harvester_set","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":"59755e76d7c3f48b"}},{"code_sha256_prefix":"9d353f13a2262a52","entry":"distributed_init","repo":"thompsonb/fairseq-smrt","repo_kind":"listed","path":"fairseq/distributed_utils.py","file_url":"https://github.com/thompsonb/fairseq-smrt/blob/HEAD/fairseq/distributed_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":"9d353f13a2262a52"}},{"code_sha256_prefix":"173463e3694ae78d","entry":"smrt_cross_entropy_loss","repo":"thompsonb/fairseq-smrt","repo_kind":"listed","path":"fairseq/criterions/smrt_cross_entropy.py","file_url":"https://github.com/thompsonb/fairseq-smrt/blob/HEAD/fairseq/criterions/smrt_cross_entropy.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":"173463e3694ae78d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}