{"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/unsupervised-tokenization-learning","title":"Unsupervised Tokenization Learning","arxiv_id":"2205.11443","date":"2022-05-23","proceeding":null,"authors":["Anton Kolonin","Vignav Ramesh"],"abstract":"In the presented study, we discover that the so-called \"transition freedom\" metric appears superior for unsupervised tokenization purposes in comparison to statistical metrics such as mutual information and conditional probability, providing F-measure scores in range from 0.71 to 1.0 across explored multilingual corpora. We find that different languages require different offshoots of that metric (such as derivative, variance, and \"peak values\") for successful tokenization. Larger training corpora do not necessarily result in better tokenization quality, while compressing the models by eliminating statistically weak evidence tends to improve performance. The proposed unsupervised tokenization technique provides quality better than or comparable to lexicon-based ones, depending on the language.","url_abs":"https://arxiv.org/abs/2205.11443v4","url_pdf":"https://arxiv.org/pdf/2205.11443v4.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":"text-segmentation","task_name":"Text Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.11443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11443"}},"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/brightmart/nlp_chinese_cor","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/aigents/pyg","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/aigents/pygents","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":23},"by_repo_kind":{"found_in_text":{"samples":23,"ran":0,"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":"912b675b8c7c6a75","entry":"build_ngrams","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/aigents_api.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/aigents_api.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"912b675b8c7c6a75"}},{"code_sha256_prefix":"59926e7aef683e3f","entry":"df2labeled","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/recognition_evaluators.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/recognition_evaluators.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"59926e7aef683e3f"}},{"code_sha256_prefix":"4e172bf386f23e2a","entry":"dict_update","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/util.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e172bf386f23e2a"}},{"code_sha256_prefix":"c7016a4ceaa87df3","entry":"dictval","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/recognition_evaluators.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/recognition_evaluators.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7016a4ceaa87df3"}},{"code_sha256_prefix":"924351cd992f8c13","entry":"get_char_grams","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/text_matching.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/text_matching.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"924351cd992f8c13"}},{"code_sha256_prefix":"3a7ff583d1404eeb","entry":"language_metrics","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/recognition_evaluators.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/recognition_evaluators.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a7ff583d1404eeb"}},{"code_sha256_prefix":"e98c31b3949ba902","entry":"listofpairs_compress_with_loss","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/util.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e98c31b3949ba902"}},{"code_sha256_prefix":"89b3155ee6b61a1e","entry":"make_annotations","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/plot.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/plot.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89b3155ee6b61a1e"}},{"code_sha256_prefix":"cbde932c8e4ed394","entry":"overlap_dic","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/cluster.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/cluster.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cbde932c8e4ed394"}},{"code_sha256_prefix":"d3bfdab19b511faf","entry":"overlap_dic2","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/cluster.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/cluster.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3bfdab19b511faf"}},{"code_sha256_prefix":"9e8c248953e7f548","entry":"overlap_dic_parts","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/cluster.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/cluster.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e8c248953e7f548"}},{"code_sha256_prefix":"b6e9d3a1691a13dc","entry":"plot_profile_freedoms","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/plot.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/plot.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6e9d3a1691a13dc"}},{"code_sha256_prefix":"da81ffd6065a7b97","entry":"plot_profile_probabilities","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/plot.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/plot.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da81ffd6065a7b97"}},{"code_sha256_prefix":"cda2aa6e82050ecf","entry":"psy_metric_lists","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/text_metrics.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/text_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cda2aa6e82050ecf"}},{"code_sha256_prefix":"31208a071423c4b0","entry":"psy_metric_texts","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/text_metrics.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/text_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31208a071423c4b0"}},{"code_sha256_prefix":"3d87a7b7834c6ee7","entry":"token_valid","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/aigents_api.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/aigents_api.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d87a7b7834c6ee7"}},{"code_sha256_prefix":"a2ee6c7e85681666","entry":"tokenize_detaching_head","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/token.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/token.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2ee6c7e85681666"}},{"code_sha256_prefix":"0cacbc8c662d91c4","entry":"tokenize_detaching_tail","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/token.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/token.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0cacbc8c662d91c4"}},{"code_sha256_prefix":"1f256c8b6febc983","entry":"tokenize_split_with_delimiters_and_quotes","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/token.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/token.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f256c8b6febc983"}},{"code_sha256_prefix":"243576c5e6ff430f","entry":"url_lines","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/text.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/text.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"243576c5e6ff430f"}},{"code_sha256_prefix":"f1455e9f0f77bdbd","entry":"url_text","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/text.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/text.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1455e9f0f77bdbd"}},{"code_sha256_prefix":"3af09d918889fc4f","entry":"url_text_lines","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/text.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/text.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3af09d918889fc4f"}},{"code_sha256_prefix":"bcc2770705085eb4","entry":"vector_proximity","repo":"aigents/pygents","repo_kind":"found_in_text","path":"pygents/util.py","file_url":"https://github.com/aigents/pygents/blob/HEAD/pygents/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bcc2770705085eb4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}