{"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/it-s-not-greek-to-mbert-inducing-word-level","title":"It's not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT","arxiv_id":"2010.08275","date":"2020-10-16","proceeding":null,"authors":["Hila Gonen","Shauli Ravfogel","Yanai Elazar","Yoav Goldberg"],"abstract":"Recent works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages. We study the word-level translation information embedded in mBERT and present two simple methods that expose remarkable translation capabilities with no fine-tuning. The results suggest that most of this information is encoded in a non-linear way, while some of it can also be recovered with purely linear tools. As part of our analysis, we test the hypothesis that mBERT learns representations which contain both a language-encoding component and an abstract, cross-lingual component, and explicitly identify an empirical language-identity subspace within mBERT representations.","url_abs":"https://arxiv.org/abs/2010.08275v1","url_pdf":"https://arxiv.org/pdf/2010.08275v1.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":"it-s-not-greek-to-mbert-inducing-word-level","repo_url":"https://github.com/gonenhila/mbert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"},{"method_slug":"mbert","method_name":"mBERT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.08275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08275"}},"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/gonenhila/mbert","reach":null}],"summary":{"ran_draft_wrong":3,"ran_honours":2,"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":"6c9282e8ef3e3619","entry":"create_repr_per_lang","repo":"gonenhila/mbert","repo_kind":"official","path":"source/analogies.py","file_url":"https://github.com/gonenhila/mbert/blob/HEAD/source/analogies.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c9282e8ef3e3619"}},{"code_sha256_prefix":"1b63ce3a8e624e66","entry":"extract_lang_mapping","repo":"gonenhila/mbert","repo_kind":"official","path":"source/translator.py","file_url":"https://github.com/gonenhila/mbert/blob/HEAD/source/translator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1b63ce3a8e624e66"}},{"code_sha256_prefix":"d772ecce38adfa72","entry":"extract_repr_random_token_bert_mlm","repo":"gonenhila/mbert","repo_kind":"official","path":"source/analogies.py","file_url":"https://github.com/gonenhila/mbert/blob/HEAD/source/analogies.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d772ecce38adfa72"}},{"code_sha256_prefix":"0a6468d8e8c1c616","entry":"get_predictions","repo":"gonenhila/mbert","repo_kind":"official","path":"source/compare_translator_analogies.py","file_url":"https://github.com/gonenhila/mbert/blob/HEAD/source/compare_translator_analogies.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0a6468d8e8c1c616"}},{"code_sha256_prefix":"7e1e5568bc1ae8da","entry":"get_repr_from_template","repo":"gonenhila/mbert","repo_kind":"official","path":"source/translator.py","file_url":"https://github.com/gonenhila/mbert/blob/HEAD/source/translator.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e1e5568bc1ae8da"}},{"code_sha256_prefix":"7252364f914f637f","entry":"collect_data_per_lang","repo":"gonenhila/mbert","repo_kind":"official","path":"source/analogies.py","file_url":"https://github.com/gonenhila/mbert/blob/HEAD/source/analogies.py","link_basis":"first_harvest_node","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":"7252364f914f637f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}