{"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/improving-multilingual-models-with-language","title":"Improving Multilingual Models with Language-Clustered Vocabularies","arxiv_id":"2010.12777","date":"2020-10-24","proceeding":"EMNLP 2020 11","authors":["Hyung Won Chung","Dan Garrette","Kiat Chuan Tan","Jason Riesa"],"abstract":"State-of-the-art multilingual models depend on vocabularies that cover all of the languages the model will expect to see at inference time, but the standard methods for generating those vocabularies are not ideal for massively multilingual applications. In this work, we introduce a novel procedure for multilingual vocabulary generation that combines the separately trained vocabularies of several automatically derived language clusters, thus balancing the trade-off between cross-lingual subword sharing and language-specific vocabularies. Our experiments show improvements across languages on key multilingual benchmark tasks TyDi QA (+2.9 F1), XNLI (+2.1\\%), and WikiAnn NER (+2.8 F1) and factor of 8 reduction in out-of-vocabulary rate, all without increasing the size of the model or data.","url_abs":"https://arxiv.org/abs/2010.12777v1","url_pdf":"https://arxiv.org/pdf/2010.12777v1.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":[],"tasks":[{"task_slug":"cg","task_name":"NER"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.12777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.12777"}},"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":"deterministic:regex_extraction","url":"https://github.com/afshinrahimi/mmner","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/google-researchdatasets/tydiqa","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran_violates":1,"ran":1,"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"found_in_text":{"samples":12,"ran":3,"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":"59c0d53cfcbb2398","entry":"average_vars","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"variables.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/variables.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59c0d53cfcbb2398"}},{"code_sha256_prefix":"a585b44308980803","entry":"softmax","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"models.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/models.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a585b44308980803"}},{"code_sha256_prefix":"3880e32be4fd7c7f","entry":"subtract_vars","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"variables.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/variables.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3880e32be4fd7c7f"}},{"code_sha256_prefix":"f6f2ba25467fd36a","entry":"check_num_records","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/utils.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":"f6f2ba25467fd36a"}},{"code_sha256_prefix":"0289bb6405576064","entry":"check_num_records_by_content","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/utils.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":"0289bb6405576064"}},{"code_sha256_prefix":"2f4055c62a01cc2c","entry":"collect_vocab_and_tags","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/utils.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":"2f4055c62a01cc2c"}},{"code_sha256_prefix":"620ac62b88277cbd","entry":"get_chunk_type","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"models.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/models.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":"620ac62b88277cbd"}},{"code_sha256_prefix":"204d8fb2bfa6564f","entry":"get_processing_word","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"config.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/config.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":"204d8fb2bfa6564f"}},{"code_sha256_prefix":"384baa37e7d09ae3","entry":"get_vocabs","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"config.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/config.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":"384baa37e7d09ae3"}},{"code_sha256_prefix":"382960e74b17b40a","entry":"interpolate_vars","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"variables.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/variables.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":"382960e74b17b40a"}},{"code_sha256_prefix":"b1e144bdab6449a6","entry":"load_vocab","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"config.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/config.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":"b1e144bdab6449a6"}},{"code_sha256_prefix":"ef651ba41fdc6cad","entry":"pad_sequences","repo":"afshinrahimi/mmner","repo_kind":"found_in_text","path":"models.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/models.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":"ef651ba41fdc6cad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}