{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/gradient-based-subword-tokenization","slug":"gradient-based-subword-tokenization","name":"Gradient-Based Subword Tokenization","full_name":"GBST","full_name_withheld":false,"description_markdown":"**GBST**, or **Gradient-based Subword Tokenization Module**, is a soft gradient-based subword tokenization module that automatically learns latent subword representations from characters in a data-driven fashion. Concretely, GBST enumerates candidate subword blocks and learns to score them in a position-wise fashion using a block scoring network.  \r\n\r\nGBST learns a position-wise soft selection over candidate subword blocks by scoring them with a scoring network. In contrast to prior tokenization-free methods, GBST learns interpretable latent subwords, which enables easy inspection of lexical representations and is more efficient than other byte-based models.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","paper":"/paper/charformer-fast-character-transformers-via","first_author":"Yi Tay","n_authors":10,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/charformer-fast-character-transformers-via"},"source":{"url":"https://arxiv.org/abs/2106.12672v3","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/google-research/google-research/blob/master/charformer/lib/charformer_layers.py","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Subword Segmentation","url":"/methods/category/subword-segmentation","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":5,"papers_newest_first":[{"paper":"/paper/charformer-a-glyph-fusion-based-attentive","slug":"charformer-a-glyph-fusion-based-attentive","title":"CharFormer: A Glyph Fusion based Attentive Framework for High-precision Character Image Denoising","date":"2022-07-16","arxiv_id":"2207.07798","n_code_links":1,"syntology":null},{"paper":"/paper/patching-leaks-in-the-charformer-for-1","slug":"patching-leaks-in-the-charformer-for-1","title":"Patching Leaks in the Charformer for Efficient Character-Level Generation","date":"2022-05-27","arxiv_id":"2205.14086","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-new-generation-of-perspective-api-efficient","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","date":"2022-02-22","arxiv_id":"2202.11176","n_code_links":0,"syntology":null},{"paper":null,"slug":"patching-leaks-in-the-charformer-for","title":"Patching Leaks in the Charformer for Generative Tasks","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/charformer-fast-character-transformers-via","slug":"charformer-fast-character-transformers-via","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","date":"2021-06-23","arxiv_id":"2106.12672","n_code_links":2,"syntology":{"ran":7,"of":10,"n_ran_checked":4,"n_instrument":3,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":5,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":5,"with_a_code_link":3,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":5,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/gradient-based-subword-tokenization/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/gradient-based-subword-tokenization/papers/ran/1","json":"/method/gradient-based-subword-tokenization/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/nmt","name":"NMT","papers":2},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/image-denoising","name":"Image Denoising","papers":1},{"task":"/task/inductive-bias","name":"Inductive Bias","papers":1},{"task":"/task/linguistic-acceptability","name":"Linguistic Acceptability","papers":1},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":1},{"task":"/task/paraphrase-identification","name":"Paraphrase Identification","papers":1},{"task":"/task/semantic-textual-similarity","name":"Semantic Textual Similarity","papers":1},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":1},{"task":"/task/toxic-comment-classification","name":"Toxic Comment Classification","papers":1},{"task":"/task/translation","name":"Translation","papers":1}],"tasks_shown":12,"n_tasks":12,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":4}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/gradient-based-subword-tokenization"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Gradient-Based%20Subword%20Tokenization","read_at":"2026-10-05T00:57:11+00:00","query":"Gradient-Based Subword Tokenization","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2106.12672","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Gradient-Based Subword Tokenization' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["gradient EM","Gradient Cuff","Gradient Mirage","phantom gradient","Gradient Surgery","pathway gradient","Gradient Surgery","Gradient Sealing"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"306960f820938066a0474727ce5c9e2d180a638836c74301cb968f295c2492eb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}