{"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/oolong-investigating-what-makes-crosslingual","title":"Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies","arxiv_id":"2202.12312","date":"2022-02-24","proceeding":null,"authors":["Zhengxuan Wu","Alex Tamkin","Isabel Papadimitriou"],"abstract":"When we transfer a pretrained language model to a new language, there are many axes of variation that change at once. To disentangle the impact of different factors like syntactic similarity and vocabulary similarity, we propose a set of controlled transfer studies: we systematically transform the language of the GLUE benchmark, altering one axis of crosslingual variation at a time, and then measure the resulting drops in a pretrained model's downstream performance. We find that models can largely recover from syntactic-style shifts, but cannot recover from vocabulary misalignment and embedding matrix re-initialization, even with continued pretraining on 15 million tokens. %On the other hand, transferring to a dataset with an unaligned vocabulary is extremely hard to recover from in the low-data regime. Moreover, good-quality tokenizers in the transfer language do not make vocabulary alignment easier. Our experiments provide insights into the factors of cross-lingual transfer that researchers should most focus on when designing language transfer scenarios.","url_abs":"https://arxiv.org/abs/2202.12312v2","url_pdf":"https://arxiv.org/pdf/2202.12312v2.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":"oolong-investigating-what-makes-crosslingual","repo_url":"https://github.com/frankaging/oolong-crosslingual","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":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.12312","atlas_url":"https://app.syntology.ai/?focus=2202.12312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.12312"}},"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/frankaging/oolong-crosslingual","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":5},"by_repo_kind":{"official":{"samples":9,"ran":4,"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":"01cef84e269d1dc7","entry":"corrupt_translator","repo":"frankaging/oolong-crosslingual","repo_kind":"official","path":"code/vocab_mismatch_utils.py","file_url":"https://github.com/frankaging/oolong-crosslingual/blob/HEAD/code/vocab_mismatch_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":"01cef84e269d1dc7"}},{"code_sha256_prefix":"6860ab9d30e0464d","entry":"full_ternary_class_func","repo":"frankaging/oolong-crosslingual","repo_kind":"official","path":"code/data_formatter_utils.py","file_url":"https://github.com/frankaging/oolong-crosslingual/blob/HEAD/code/data_formatter_utils.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":"6860ab9d30e0464d"}},{"code_sha256_prefix":"3615aa2c7e9b72b4","entry":"only_three","repo":"frankaging/oolong-crosslingual","repo_kind":"official","path":"code/data_formatter_utils.py","file_url":"https://github.com/frankaging/oolong-crosslingual/blob/HEAD/code/data_formatter_utils.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":"3615aa2c7e9b72b4"}},{"code_sha256_prefix":"c0154fb85012901c","entry":"rotate","repo":"frankaging/oolong-crosslingual","repo_kind":"official","path":"code/vocab_mismatch_utils.py","file_url":"https://github.com/frankaging/oolong-crosslingual/blob/HEAD/code/vocab_mismatch_utils.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":"c0154fb85012901c"}},{"code_sha256_prefix":"073dcae3d701d327","entry":"process_large_review","repo":"frankaging/oolong-crosslingual","repo_kind":"official","path":"code/data_formatter_utils.py","file_url":"https://github.com/frankaging/oolong-crosslingual/blob/HEAD/code/data_formatter_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":true,"mcp_get_code":{"code_sha256":"073dcae3d701d327"}},{"code_sha256_prefix":"902063b35348d6a3","entry":"random_corrupt","repo":"frankaging/oolong-crosslingual","repo_kind":"official","path":"code/run_fine_tuning.py","file_url":"https://github.com/frankaging/oolong-crosslingual/blob/HEAD/code/run_fine_tuning.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":"902063b35348d6a3"}},{"code_sha256_prefix":"d804271ce3d48986","entry":"random_corrupt","repo":"frankaging/oolong-crosslingual","repo_kind":"official","path":"code/run_glue_deberta.py","file_url":"https://github.com/frankaging/oolong-crosslingual/blob/HEAD/code/run_glue_deberta.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":"d804271ce3d48986"}},{"code_sha256_prefix":"0233dd24ae6a5801","entry":"random_corrupt","repo":"frankaging/oolong-crosslingual","repo_kind":"official","path":"code/run_glue_xlmr.py","file_url":"https://github.com/frankaging/oolong-crosslingual/blob/HEAD/code/run_glue_xlmr.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":"0233dd24ae6a5801"}},{"code_sha256_prefix":"4c3223317071adb8","entry":"random_corrupt","repo":"frankaging/oolong-crosslingual","repo_kind":"official","path":"code/run_mid_tuning.py","file_url":"https://github.com/frankaging/oolong-crosslingual/blob/HEAD/code/run_mid_tuning.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":"4c3223317071adb8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}