{"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/non-parametric-unsupervised-domain-adaptation","title":"Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation","arxiv_id":"2109.06604","date":"2021-09-14","proceeding":"Findings (EMNLP) 2021 11","authors":["Xin Zheng","Zhirui Zhang","ShuJian Huang","Boxing Chen","Jun Xie","Weihua Luo","Jiajun Chen"],"abstract":"Recently, $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation without retraining. Despite being conceptually attractive, it heavily relies on high-quality in-domain parallel corpora, limiting its capability on unsupervised domain adaptation, where in-domain parallel corpora are scarce or nonexistent. In this paper, we propose a novel framework that directly uses in-domain monolingual sentences in the target language to construct an effective datastore for $k$-nearest-neighbor retrieval. To this end, we first introduce an autoencoder task based on the target language, and then insert lightweight adapters into the original NMT model to map the token-level representation of this task to the ideal representation of translation task. Experiments on multi-domain datasets demonstrate that our proposed approach significantly improves the translation accuracy with target-side monolingual data, while achieving comparable performance with back-translation.","url_abs":"https://arxiv.org/abs/2109.06604v2","url_pdf":"https://arxiv.org/pdf/2109.06604v2.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":"non-parametric-unsupervised-domain-adaptation","repo_url":"https://github.com/zhengxxn/uda-knn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.06604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06604"}},"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/zhengxxn/uda-knn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"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":"88ce019380f10478","entry":"get_symbols_to_strip_from_output","repo":"zhengxxn/uda-knn","repo_kind":"official","path":"knn_generate.py","file_url":"https://github.com/zhengxxn/uda-knn/blob/HEAD/knn_generate.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"88ce019380f10478"}},{"code_sha256_prefix":"3986bbf997a3a263","entry":"add_insertion_noise","repo":"zhengxxn/uda-knn","repo_kind":"official","path":"noising_plain_text.py","file_url":"https://github.com/zhengxxn/uda-knn/blob/HEAD/noising_plain_text.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":"3986bbf997a3a263"}},{"code_sha256_prefix":"4fc1f4d5c32625fd","entry":"define_mask_span_distribution","repo":"zhengxxn/uda-knn","repo_kind":"official","path":"noising_plain_text.py","file_url":"https://github.com/zhengxxn/uda-knn/blob/HEAD/noising_plain_text.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":"4fc1f4d5c32625fd"}},{"code_sha256_prefix":"9b12377ea6bd5e98","entry":"get_word_starts","repo":"zhengxxn/uda-knn","repo_kind":"official","path":"noising_plain_text.py","file_url":"https://github.com/zhengxxn/uda-knn/blob/HEAD/noising_plain_text.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":"9b12377ea6bd5e98"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}