{"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/effective-cross-lingual-transfer-of-neural","title":"Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies","arxiv_id":"1905.05475","date":"2019-05-14","proceeding":"ACL 2019 7","authors":["Yunsu Kim","Yingbo Gao","Hermann Ney"],"abstract":"Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques to transfer a pre-trained NMT model to a new, unrelated language without shared vocabularies. We relieve the vocabulary mismatch by using cross-lingual word embedding, train a more language-agnostic encoder by injecting artificial noises, and generate synthetic data easily from the pre-training data without back-translation. Our methods do not require restructuring the vocabulary or retraining the model. We improve plain NMT transfer by up to +5.1% BLEU in five low-resource translation tasks, outperforming multilingual joint training by a large margin. We also provide extensive ablation studies on pre-trained embedding, synthetic data, vocabulary size, and parameter freezing for a better understanding of NMT transfer.","url_abs":"https://arxiv.org/abs/1905.05475v2","url_pdf":"https://arxiv.org/pdf/1905.05475v2.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":"effective-cross-lingual-transfer-of-neural","repo_url":"https://github.com/yunsukim86/sockeye-transfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"mxnet","reach":null}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"low-resource-neural-machine-translation-2","task_name":"Low Resource Neural Machine Translation"},{"task_slug":"low-resource-neural-machine-translation","task_name":"Low-Resource Neural Machine Translation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.05475","atlas_url":"https://app.syntology.ai/?focus=1905.05475","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}