{"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/language-aware-multilingual-machine","title":"Language-Aware Multilingual Machine Translation with Self-Supervised Learning","arxiv_id":"2302.05008","date":"2023-02-10","proceeding":null,"authors":["Haoran Xu","Jean Maillard","Vedanuj Goswami"],"abstract":"Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters. Self-supervised learning (SSL) approaches that leverage large quantities of monolingual data (where parallel data is unavailable) have shown promise by improving translation performance as complementary tasks to the MMT task. However, jointly optimizing SSL and MMT tasks is even more challenging. In this work, we first investigate how to utilize intra-distillation to learn more *language-specific* parameters and then show the importance of these language-specific parameters. Next, we propose a novel but simple SSL task, concurrent denoising, that co-trains with the MMT task by concurrently denoising monolingual data on both the encoder and decoder. Finally, we apply intra-distillation to this co-training approach. Combining these two approaches significantly improves MMT performance, outperforming three state-of-the-art SSL methods by a large margin, e.g., 11.3\\% and 3.7\\% improvement on an 8-language and a 15-language benchmark compared with MASS, respectively","url_abs":"https://arxiv.org/abs/2302.05008v1","url_pdf":"https://arxiv.org/pdf/2302.05008v1.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":"language-aware-multilingual-machine","repo_url":"https://github.com/fe1ixxu/cd_id_mmt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.05008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.05008"}},"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/fe1ixxu/cd_id_mmt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"40da82fb5505ec77","entry":"get_m20_mean","repo":"fe1ixxu/cd_id_mmt","repo_kind":"official","path":"get_m15_mean_score.py","file_url":"https://github.com/fe1ixxu/cd_id_mmt/blob/HEAD/get_m15_mean_score.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":"40da82fb5505ec77"}},{"code_sha256_prefix":"a7d4fd432396c3a4","entry":"is_checkpoint_sharded","repo":"fe1ixxu/cd_id_mmt","repo_kind":"official","path":"fairseq/checkpoint_utils.py","file_url":"https://github.com/fe1ixxu/cd_id_mmt/blob/HEAD/fairseq/checkpoint_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":"a7d4fd432396c3a4"}},{"code_sha256_prefix":"fce0ae1267eb484d","entry":"loss_unstructured","repo":"fe1ixxu/cd_id_mmt","repo_kind":"official","path":"prune.py","file_url":"https://github.com/fe1ixxu/cd_id_mmt/blob/HEAD/prune.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":"fce0ae1267eb484d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}