{"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/shuowen-jiezi-linguistically-informed","title":"Sub-Character Tokenization for Chinese Pretrained Language Models","arxiv_id":"2106.00400","date":"2021-06-01","proceeding":null,"authors":["Chenglei Si","Zhengyan Zhang","Yingfa Chen","Fanchao Qi","Xiaozhi Wang","Zhiyuan Liu","Yasheng Wang","Qun Liu","Maosong Sun"],"abstract":"Tokenization is fundamental to pretrained language models (PLMs). Existing tokenization methods for Chinese PLMs typically treat each character as an indivisible token. However, they ignore the unique feature of the Chinese writing system where additional linguistic information exists below the character level, i.e., at the sub-character level. To utilize such information, we propose sub-character (SubChar for short) tokenization. Specifically, we first encode the input text by converting each Chinese character into a short sequence based on its glyph or pronunciation, and then construct the vocabulary based on the encoded text with sub-word segmentation. Experimental results show that SubChar tokenizers have two main advantages over existing tokenizers: 1) They can tokenize inputs into much shorter sequences, thus improving the computational efficiency. 2) Pronunciation-based SubChar tokenizers can encode Chinese homophones into the same transliteration sequences and produce the same tokenization output, hence being robust to homophone typos. At the same time, models trained with SubChar tokenizers perform competitively on downstream tasks. We release our code and models at https://github.com/thunlp/SubCharTokenization to facilitate future work.","url_abs":"https://arxiv.org/abs/2106.00400v3","url_pdf":"https://arxiv.org/pdf/2106.00400v3.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":"shuowen-jiezi-linguistically-informed","repo_url":"https://github.com/thunlp/subchartokenization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"shuowen-jiezi-linguistically-informed","repo_url":"https://github.com/thunlp/readin","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"chinese-word-segmentation","task_name":"Chinese Word Segmentation"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"transliteration","task_name":"Transliteration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.00400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00400"}},"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/thunlp/subchartokenization","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thunlp/readin","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":4,"samples":[{"code_sha256_prefix":"cac113ca87b9d9f3","entry":"acc_and_f1","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"cac113ca87b9d9f3"}},{"code_sha256_prefix":"7d7c4b508dbf03cd","entry":"compute_metrics","repo":"thunlp/subchartokenization","repo_kind":"official","path":"run_glue.py","file_url":"https://github.com/thunlp/subchartokenization/blob/HEAD/run_glue.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d7c4b508dbf03cd"}},{"code_sha256_prefix":"3c19c25e49f8b32f","entry":"load_dict","repo":"thunlp/subchartokenization","repo_kind":"official","path":"data/convert_corpus.py","file_url":"https://github.com/thunlp/subchartokenization/blob/HEAD/data/convert_corpus.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c19c25e49f8b32f"}},{"code_sha256_prefix":"3c241ecfe3749a6d","entry":"simple_accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3c241ecfe3749a6d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}