{"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/gender-bias-in-multilingual-embeddings-and","title":"Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer","arxiv_id":"2005.00699","date":"2020-05-02","proceeding":"ACL 2020 6","authors":["Jieyu Zhao","Subhabrata Mukherjee","Saghar Hosseini","Kai-Wei Chang","Ahmed Hassan Awadallah"],"abstract":"Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings, such as cross-lingual transfer, where a natural language processing (NLP) model trained on one language is deployed to another language. While the cross-lingual transfer techniques are powerful, they carry gender bias from the source to target languages. In this paper, we study gender bias in multilingual embeddings and how it affects transfer learning for NLP applications. We create a multilingual dataset for bias analysis and propose several ways for quantifying bias in multilingual representations from both the intrinsic and extrinsic perspectives. Experimental results show that the magnitude of bias in the multilingual representations changes differently when we align the embeddings to different target spaces and that the alignment direction can also have an influence on the bias in transfer learning. We further provide recommendations for using the multilingual word representations for downstream tasks.","url_abs":"https://arxiv.org/abs/2005.00699v1","url_pdf":"https://arxiv.org/pdf/2005.00699v1.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":"gender-bias-in-multilingual-embeddings-and","repo_url":"https://github.com/msr-lit/multilingualbias","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.00699","atlas_url":"https://app.syntology.ai/?focus=2005.00699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00699"}},"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/msr-lit/multilingualbias","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"unverified":4},"by_repo_kind":{"listed":{"samples":12,"ran":8,"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":12,"samples":[{"code_sha256_prefix":"34530fbdde2cb8fe","entry":"dedup_middle","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/replicateMLBs/DE/preprocess_de.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/replicateMLBs/DE/preprocess_de.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":false,"mcp_get_code":{"code_sha256":"34530fbdde2cb8fe"}},{"code_sha256_prefix":"d308860a48dbe40d","entry":"get_sequences_lengths","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/bios_codes/utils.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/bios_codes/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":false,"mcp_get_code":{"code_sha256":"d308860a48dbe40d"}},{"code_sha256_prefix":"c2394da354f9fe76","entry":"infer_gender","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/replicateMLBs/DE/down_de_bios.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/replicateMLBs/DE/down_de_bios.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":false,"mcp_get_code":{"code_sha256":"c2394da354f9fe76"}},{"code_sha256_prefix":"ee32fe610b551817","entry":"infer_gender","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/replicateMLBs/ES/download_es_bios.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/replicateMLBs/ES/download_es_bios.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":false,"mcp_get_code":{"code_sha256":"ee32fe610b551817"}},{"code_sha256_prefix":"be8c2c987a279534","entry":"infer_gender","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/replicateMLBs/FR/download_fr_bios.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/replicateMLBs/FR/download_fr_bios.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":false,"mcp_get_code":{"code_sha256":"be8c2c987a279534"}},{"code_sha256_prefix":"afbe2e1ae156e07e","entry":"parse_args","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/bios_codes/config.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/bios_codes/config.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":false,"mcp_get_code":{"code_sha256":"afbe2e1ae156e07e"}},{"code_sha256_prefix":"58ffc257d9f94fd1","entry":"softmax_masked","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/bios_codes/utils.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/bios_codes/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":false,"mcp_get_code":{"code_sha256":"58ffc257d9f94fd1"}},{"code_sha256_prefix":"6a750bc656206858","entry":"to_device","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/bios_codes/utils.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/bios_codes/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":false,"mcp_get_code":{"code_sha256":"6a750bc656206858"}},{"code_sha256_prefix":"5bc8cc37fb144264","entry":"extract_name","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/replicateMLBs/ES/download_es_bios.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/replicateMLBs/ES/download_es_bios.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":false,"mcp_get_code":{"code_sha256":"5bc8cc37fb144264"}},{"code_sha256_prefix":"a726daef874a3d4e","entry":"group_by","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/replicateMLBs/DE/preprocess_de.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/replicateMLBs/DE/preprocess_de.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":false,"mcp_get_code":{"code_sha256":"a726daef874a3d4e"}},{"code_sha256_prefix":"019de8c1d879acd4","entry":"load_pkl","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/replicateMLBs/DE/preprocess_de.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/replicateMLBs/DE/preprocess_de.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":false,"mcp_get_code":{"code_sha256":"019de8c1d879acd4"}},{"code_sha256_prefix":"f7b10b80fcb10ccf","entry":"re_escape_title","repo":"msr-lit/multilingualbias","repo_kind":"listed","path":"extrinsic/replicateMLBs/DE/down_de_bios.py","file_url":"https://github.com/msr-lit/multilingualbias/blob/HEAD/extrinsic/replicateMLBs/DE/down_de_bios.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":false,"mcp_get_code":{"code_sha256":"f7b10b80fcb10ccf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}