{"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/overlap-based-vocabulary-generation-improves","title":"Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages","arxiv_id":"2203.01976","date":"2022-03-03","proceeding":"ACL 2022 5","authors":["Vaidehi Patil","Partha Talukdar","Sunita Sarawagi"],"abstract":"Pre-trained multilingual language models such as mBERT and XLM-R have demonstrated great potential for zero-shot cross-lingual transfer to low web-resource languages (LRL). However, due to limited model capacity, the large difference in the sizes of available monolingual corpora between high web-resource languages (HRL) and LRLs does not provide enough scope of co-embedding the LRL with the HRL, thereby affecting downstream task performance of LRLs. In this paper, we argue that relatedness among languages in a language family along the dimension of lexical overlap may be leveraged to overcome some of the corpora limitations of LRLs. We propose Overlap BPE (OBPE), a simple yet effective modification to the BPE vocabulary generation algorithm which enhances overlap across related languages. Through extensive experiments on multiple NLP tasks and datasets, we observe that OBPE generates a vocabulary that increases the representation of LRLs via tokens shared with HRLs. This results in improved zero-shot transfer from related HRLs to LRLs without reducing HRL representation and accuracy. Unlike previous studies that dismissed the importance of token-overlap, we show that in the low-resource related language setting, token overlap matters. Synthetically reducing the overlap to zero can cause as much as a four-fold drop in zero-shot transfer accuracy.","url_abs":"https://arxiv.org/abs/2203.01976v2","url_pdf":"https://arxiv.org/pdf/2203.01976v2.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":"overlap-based-vocabulary-generation-improves","repo_url":"https://github.com/vaidehi99/obpe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"xlm-r","task_name":"XLM-R"},{"task_slug":"zero-shot-cross-lingual-transfer","task_name":"Zero-Shot Cross-Lingual Transfer"}],"methods":[{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"xlm-r","method_name":"XLM-R"},{"method_slug":"mbert","method_name":"mBERT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01976"}},"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/vaidehi99/obpe","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Vaidehi99/OBPE","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"ran_violates":2,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"cafcf2e2bf72ef8f","entry":"BPEMultiTokenizer","repo":"Vaidehi99/OBPE","repo_kind":"official","path":"tokenizer.py","file_url":"https://github.com/Vaidehi99/OBPE/blob/HEAD/tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cafcf2e2bf72ef8f"}},{"code_sha256_prefix":"afcc525dbe642c99","entry":"MaxHeap","repo":"Vaidehi99/OBPE","repo_kind":"official","path":"tokenizer.py","file_url":"https://github.com/Vaidehi99/OBPE/blob/HEAD/tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"afcc525dbe642c99"}},{"code_sha256_prefix":"d2a283c11f4d77c5","entry":"MultilingualTokenizer","repo":"Vaidehi99/OBPE","repo_kind":"official","path":"tokenizer.py","file_url":"https://github.com/Vaidehi99/OBPE/blob/HEAD/tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d2a283c11f4d77c5"}},{"code_sha256_prefix":"8ebaf21ef830e017","entry":"get_vocabulary","repo":"Vaidehi99/OBPE","repo_kind":"official","path":"tokenizer.py","file_url":"https://github.com/Vaidehi99/OBPE/blob/HEAD/tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ebaf21ef830e017"}},{"code_sha256_prefix":"8ee61df5b2ed5679","entry":"softmin_lin","repo":"Vaidehi99/OBPE","repo_kind":"official","path":"tokenizer.py","file_url":"https://github.com/Vaidehi99/OBPE/blob/HEAD/tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ee61df5b2ed5679"}},{"code_sha256_prefix":"ee213767175a98b3","entry":"softmin_log","repo":"Vaidehi99/OBPE","repo_kind":"official","path":"tokenizer.py","file_url":"https://github.com/Vaidehi99/OBPE/blob/HEAD/tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ee213767175a98b3"}},{"code_sha256_prefix":"c29a31a49b9a683e","entry":"_get_vocabulary","repo":"Vaidehi99/OBPE","repo_kind":"official","path":"tokenizer.py","file_url":"https://github.com/Vaidehi99/OBPE/blob/HEAD/tokenizer.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":"c29a31a49b9a683e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}