{"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/nearest-neighbour-few-shot-learning-for-cross","title":"Nearest Neighbour Few-Shot Learning for Cross-lingual Classification","arxiv_id":"2109.02221","date":"2021-09-06","proceeding":"EMNLP 2021 11","authors":["M Saiful Bari","Batool Haider","Saab Mansour"],"abstract":"Even though large pre-trained multilingual models (e.g. mBERT, XLM-R) have led to significant performance gains on a wide range of cross-lingual NLP tasks, success on many downstream tasks still relies on the availability of sufficient annotated data. Traditional fine-tuning of pre-trained models using only a few target samples can cause over-fitting. This can be quite limiting as most languages in the world are under-resourced. In this work, we investigate cross-lingual adaptation using a simple nearest neighbor few-shot (<15 samples) inference technique for classification tasks. We experiment using a total of 16 distinct languages across two NLP tasks- XNLI and PAWS-X. Our approach consistently improves traditional fine-tuning using only a handful of labeled samples in target locales. We also demonstrate its generalization capability across tasks.","url_abs":"https://arxiv.org/abs/2109.02221v1","url_pdf":"https://arxiv.org/pdf/2109.02221v1.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":"nearest-neighbour-few-shot-learning-for-cross","repo_url":"https://github.com/amazon-research/nearest-neighbor-crosslingual-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"xlm-r","task_name":"XLM-R"}],"methods":[{"method_slug":"mbert","method_name":"mBERT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.02221","atlas_url":"https://app.syntology.ai/?focus=2109.02221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.02221"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/amazon-research/nearest-neighbor-crosslingual-classification","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/amazon-research/nearest-neighborcrosslingual-classification","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran":7,"unverified":3},"by_repo_kind":{"listed":{"samples":10,"ran":7,"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":0,"samples":[{"code_sha256_prefix":"81ea193467a90dc6","entry":"compute_confidence_interval","repo":"amazon-research/nearest-neighbor-crosslingual-classification","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/amazon-research/nearest-neighbor-crosslingual-classification/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81ea193467a90dc6"}},{"code_sha256_prefix":"09bfd5739bdc89aa","entry":"compute_metrics","repo":"amazon-research/nearest-neighbor-crosslingual-classification","repo_kind":"listed","path":"processors.py","file_url":"https://github.com/amazon-research/nearest-neighbor-crosslingual-classification/blob/HEAD/processors.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"09bfd5739bdc89aa"}},{"code_sha256_prefix":"c2908737996f7c62","entry":"create_logger","repo":"amazon-research/nearest-neighbor-crosslingual-classification","repo_kind":"listed","path":"logger.py","file_url":"https://github.com/amazon-research/nearest-neighbor-crosslingual-classification/blob/HEAD/logger.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2908737996f7c62"}},{"code_sha256_prefix":"6011037118e5cad1","entry":"dist_training","repo":"amazon-research/nearest-neighbor-crosslingual-classification","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/amazon-research/nearest-neighbor-crosslingual-classification/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6011037118e5cad1"}},{"code_sha256_prefix":"27e546637549edd0","entry":"eval_checkpoint","repo":"amazon-research/nearest-neighbor-crosslingual-classification","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/amazon-research/nearest-neighbor-crosslingual-classification/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"27e546637549edd0"}},{"code_sha256_prefix":"eb9737eeece5009a","entry":"meta_sample_data","repo":"amazon-research/nearest-neighbor-crosslingual-classification","repo_kind":"listed","path":"few_shot_modules.py","file_url":"https://github.com/amazon-research/nearest-neighbor-crosslingual-classification/blob/HEAD/few_shot_modules.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eb9737eeece5009a"}},{"code_sha256_prefix":"3eac0a04e50eafe0","entry":"warp_tqdm","repo":"amazon-research/nearest-neighbor-crosslingual-classification","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/amazon-research/nearest-neighbor-crosslingual-classification/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3eac0a04e50eafe0"}},{"code_sha256_prefix":"5b438d5554e101e9","entry":"get_model_class","repo":"amazon-research/nearest-neighbor-crosslingual-classification","repo_kind":"listed","path":"models.py","file_url":"https://github.com/amazon-research/nearest-neighbor-crosslingual-classification/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5b438d5554e101e9"}},{"code_sha256_prefix":"2a755c99df3f125f","entry":"load_model","repo":"amazon-research/nearest-neighbor-crosslingual-classification","repo_kind":"listed","path":"models.py","file_url":"https://github.com/amazon-research/nearest-neighbor-crosslingual-classification/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2a755c99df3f125f"}},{"code_sha256_prefix":"3c241ecfe3749a6d","entry":"simple_accuracy","repo":"amazon-research/nearest-neighbor-crosslingual-classification","repo_kind":"listed","path":"processors.py","file_url":"https://github.com/amazon-research/nearest-neighbor-crosslingual-classification/blob/HEAD/processors.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3c241ecfe3749a6d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}