{"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/zero-shot-cross-lingual-ner-using-phonemic","title":"Zero-Shot Cross-Lingual NER Using Phonemic Representations for Low-Resource Languages","arxiv_id":"2406.16030","date":"2024-06-23","proceeding":null,"authors":["Jimin Sohn","Haeji Jung","Alex Cheng","Jooeon Kang","Yilin Du","David R. Mortensen"],"abstract":"Existing zero-shot cross-lingual NER approaches require substantial prior knowledge of the target language, which is impractical for low-resource languages. In this paper, we propose a novel approach to NER using phonemic representation based on the International Phonetic Alphabet (IPA) to bridge the gap between representations of different languages. Our experiments show that our method significantly outperforms baseline models in extremely low-resource languages, with the highest average F1 score (46.38%) and lowest standard deviation (12.67), particularly demonstrating its robustness with non-Latin scripts. Our codes are available at https://github.com/Gabriel819/zeroshot_ner.git","url_abs":"https://arxiv.org/abs/2406.16030v2","url_pdf":"https://arxiv.org/pdf/2406.16030v2.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":"zero-shot-cross-lingual-ner-using-phonemic","repo_url":"https://github.com/gabriel819/zeroshot_ner","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-lingual-ner","task_name":"Cross-Lingual NER"},{"task_slug":"cg","task_name":"NER"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.16030","atlas_url":"https://app.syntology.ai/?focus=2406.16030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16030"}},"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":"deterministic:regex_extraction","url":"https://github.com/Gabriel819/zeroshot_ner","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"e144784efb74ca1a","entry":"XPhoneBertEmbeddings","repo":"Gabriel819/zeroshot_ner","repo_kind":"official","path":"model/xphonebert.py","file_url":"https://github.com/Gabriel819/zeroshot_ner/blob/HEAD/model/xphonebert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e144784efb74ca1a"}},{"code_sha256_prefix":"d4903874fdec3763","entry":"create_position_ids_from_input_ids","repo":"Gabriel819/zeroshot_ner","repo_kind":"official","path":"model/xphonebert.py","file_url":"https://github.com/Gabriel819/zeroshot_ner/blob/HEAD/model/xphonebert.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d4903874fdec3763"}},{"code_sha256_prefix":"200ce6c8d965fde9","entry":"XPhoneBertForNER","repo":"Gabriel819/zeroshot_ner","repo_kind":"official","path":"model/xphonebert.py","file_url":"https://github.com/Gabriel819/zeroshot_ner/blob/HEAD/model/xphonebert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"200ce6c8d965fde9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}