{"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/data-diversification-an-elegant-strategy-for","title":"Data Diversification: A Simple Strategy For Neural Machine Translation","arxiv_id":"1911.01986","date":"2019-11-05","proceeding":"NeurIPS 2020 12","authors":["Xuan-Phi Nguyen","Shafiq Joty","Wu Kui","Ai Ti Aw"],"abstract":"We introduce Data Diversification: a simple but effective strategy to boost neural machine translation (NMT) performance. It diversifies the training data by using the predictions of multiple forward and backward models and then merging them with the original dataset on which the final NMT model is trained. Our method is applicable to all NMT models. It does not require extra monolingual data like back-translation, nor does it add more computations and parameters like ensembles of models. Our method achieves state-of-the-art BLEU scores of 30.7 and 43.7 in the WMT'14 English-German and English-French translation tasks, respectively. It also substantially improves on 8 other translation tasks: 4 IWSLT tasks (English-German and English-French) and 4 low-resource translation tasks (English-Nepali and English-Sinhala). We demonstrate that our method is more effective than knowledge distillation and dual learning, it exhibits strong correlation with ensembles of models, and it trades perplexity off for better BLEU score. We have released our source code at https://github.com/nxphi47/data_diversification","url_abs":"https://arxiv.org/abs/1911.01986v4","url_pdf":"https://arxiv.org/pdf/1911.01986v4.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":"data-diversification-an-elegant-strategy-for","repo_url":"https://github.com/nxphi47/data_diversification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"data-diversification-an-elegant-strategy-for","repo_url":"https://github.com/nxphi47/multiagent_crosstranslate","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-iwslt2014-german","task":"Machine Translation","dataset":"IWSLT2014 German-English","model":"Data Diversification","rank_in_archive_order":12,"of":34,"metrics":{"BLEU score":"37.2"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"Data Diversification - Transformer","rank_in_archive_order":9,"of":91,"metrics":{"BLEU score":"30.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.01986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01986"}},"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/nxphi47/multiagent_crosstranslate","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nxphi47/data_diversification","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"753bedf09d6baded","entry":"default_avg_params","repo":"nxphi47/data_diversification","repo_kind":"official","path":"average_checkpoints.py","file_url":"https://github.com/nxphi47/data_diversification/blob/HEAD/average_checkpoints.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"753bedf09d6baded"}},{"code_sha256_prefix":"0f957c04872cd5bd","entry":"ema_avg_params","repo":"nxphi47/data_diversification","repo_kind":"official","path":"average_checkpoints.py","file_url":"https://github.com/nxphi47/data_diversification/blob/HEAD/average_checkpoints.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0f957c04872cd5bd"}},{"code_sha256_prefix":"4ad19f874660e39c","entry":"merge_nodup","repo":"nxphi47/data_diversification","repo_kind":"official","path":"combine_corpus.py","file_url":"https://github.com/nxphi47/data_diversification/blob/HEAD/combine_corpus.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4ad19f874660e39c"}},{"code_sha256_prefix":"fcf378b4ce4a5217","entry":"average_checkpoints","repo":"nxphi47/data_diversification","repo_kind":"official","path":"average_checkpoints.py","file_url":"https://github.com/nxphi47/data_diversification/blob/HEAD/average_checkpoints.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fcf378b4ce4a5217"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}