{"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/a-balanced-data-approach-for-evaluating-cross-1","title":"A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank","arxiv_id":"2205.04086","date":"2022-05-09","proceeding":"NAACL 2022 7","authors":["Dan Malkin","Tomasz Limisiewicz","Gabriel Stanovsky"],"abstract":"We show that the choice of pretraining languages affects downstream cross-lingual transfer for BERT-based models. We inspect zero-shot performance in balanced data conditions to mitigate data size confounds, classifying pretraining languages that improve downstream performance as donors, and languages that are improved in zero-shot performance as recipients. We develop a method of quadratic time complexity in the number of languages to estimate these relations, instead of an exponential exhaustive computation of all possible combinations. We find that our method is effective on a diverse set of languages spanning different linguistic features and two downstream tasks. Our findings can inform developers of large-scale multilingual language models in choosing better pretraining configurations.","url_abs":"https://arxiv.org/abs/2205.04086v1","url_pdf":"https://arxiv.org/pdf/2205.04086v1.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":"a-balanced-data-approach-for-evaluating-cross-1","repo_url":"https://github.com/slab-nlp/linguistic-blood-bank","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.04086","atlas_url":"https://app.syntology.ai/?focus=2205.04086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.04086"}},"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/slab-nlp/linguistic-blood-bank","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":"8069c8d50d3735e9","entry":"load_config","repo":"slab-nlp/linguistic-blood-bank","repo_kind":"official","path":"src/model/train_LM.py","file_url":"https://github.com/slab-nlp/linguistic-blood-bank/blob/HEAD/src/model/train_LM.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8069c8d50d3735e9"}},{"code_sha256_prefix":"5896136fc2e01e8e","entry":"set_edge_color","repo":"slab-nlp/linguistic-blood-bank","repo_kind":"official","path":"visualization_tool/visualization_utils/dynamic_graph_utils.py","file_url":"https://github.com/slab-nlp/linguistic-blood-bank/blob/HEAD/visualization_tool/visualization_utils/dynamic_graph_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5896136fc2e01e8e"}},{"code_sha256_prefix":"575723c72fcdcc2d","entry":"set_node_color","repo":"slab-nlp/linguistic-blood-bank","repo_kind":"official","path":"visualization_tool/visualization_utils/dynamic_graph_utils.py","file_url":"https://github.com/slab-nlp/linguistic-blood-bank/blob/HEAD/visualization_tool/visualization_utils/dynamic_graph_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"575723c72fcdcc2d"}},{"code_sha256_prefix":"9da76cbaec8f17c6","entry":"set_node_value","repo":"slab-nlp/linguistic-blood-bank","repo_kind":"official","path":"visualization_tool/visualization_utils/dynamic_graph_utils.py","file_url":"https://github.com/slab-nlp/linguistic-blood-bank/blob/HEAD/visualization_tool/visualization_utils/dynamic_graph_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9da76cbaec8f17c6"}},{"code_sha256_prefix":"1938eb2015691778","entry":"tolist","repo":"slab-nlp/linguistic-blood-bank","repo_kind":"official","path":"src/model/dataset.py","file_url":"https://github.com/slab-nlp/linguistic-blood-bank/blob/HEAD/src/model/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1938eb2015691778"}},{"code_sha256_prefix":"b52d287880b69198","entry":"show_tsne","repo":"slab-nlp/linguistic-blood-bank","repo_kind":"official","path":"visualization_tool/launch_interface.py","file_url":"https://github.com/slab-nlp/linguistic-blood-bank/blob/HEAD/visualization_tool/launch_interface.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":true,"mcp_get_code":{"code_sha256":"b52d287880b69198"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}