{"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":"/task/text-segmentation/papers/2","list_of":"/task/text-segmentation","task":"Text Segmentation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,124],"of":124,"counts":{"archive_papers_tagged":124,"with_a_code_link":40,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":124,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":1,"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"},"first_page":"/task/text-segmentation","prev":"/task/text-segmentation","next":null,"papers":[{"url":null,"slug":"color-and-gradient-features-for-text","title":"Color and Gradient Features for Text Segmentation from Video Frames","date":"2017-08-22","arxiv_id":"1708.06561","repositories_listed":0,"syntology":null},{"url":null,"slug":"protein-word-detection-using-text","title":"Protein Word Detection using Text Segmentation Techniques","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-text-segmentation-based-on","title":"Unsupervised Text Segmentation Based on Native Language Characteristics","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-extraction-from-texture-images-using","title":"Text Extraction From Texture Images Using Masked Signal Decomposition","date":"2017-06-11","arxiv_id":"1706.04041","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-segmentation-using-named-entity","title":"Text Segmentation using Named Entity Recognition and Co-reference Resolution in English and Greek Texts","date":"2016-10-28","arxiv_id":"1610.09226","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-annotated-corpus-and-method-for-analysis","title":"An Annotated Corpus and Method for Analysis of Ad-Hoc Structures Embedded in Text","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-segmentation-of-digitized-clinical-texts","title":"Text Segmentation of Digitized Clinical Texts","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"zipfs-law-is-a-consequence-of-coherent","title":"Zipf's law is a consequence of coherent language production","date":"2016-01-29","arxiv_id":"1601.07969","repositories_listed":0,"syntology":null},{"url":null,"slug":"ontoseg-a-novel-approach-to-text-segmentation","title":"OntoSeg: a Novel Approach to Text Segmentation using Ontological Similarity","date":"2015-11-26","arxiv_id":"1511.08411","repositories_listed":0,"syntology":null},{"url":null,"slug":"turn-segmentation-into-utterances-for-arabic","title":"Turn Segmentation into Utterances for Arabic Spontaneous Dialogues and Instance Messages","date":"2015-05-12","arxiv_id":"1505.03081","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-news-source-detection-in-twitter","title":"Automatic News Source Detection in Twitter Based on Text Segmentation","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-abbreviations-using-google-books","title":"Generating abbreviations using Google Books library","date":"2014-10-04","arxiv_id":"1410.1080","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-segmenter-for-chinese-micro-blogging","title":"Word Segmenter for Chinese Micro-blogging Text Segmentation -- Report for CIPS-SIGHAN'2014 Bakeoff","date":"2014-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-text-segmentation-algorithms-for-the","title":"Using Text Segmentation Algorithms for the Automatic Generation of E-Learning Courses","date":"2014-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-fast-hierarchical-method-for-multi-script","title":"A Fast Hierarchical Method for Multi-script and Arbitrary Oriented Scene Text Extraction","date":"2014-07-28","arxiv_id":"1407.7504","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-segmentation-with-character-level-text","title":"Text segmentation with character-level text embeddings","date":"2013-09-18","arxiv_id":"1309.4628","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-segmentation-for-language-identification","title":"Text segmentation for Language Identification in Greek Forums","date":"2013-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-text-segmentation-using-boundary","title":"Evaluating Text Segmentation using Boundary Edit Distance","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-text-segmentation-for-index-term","title":"Bayesian Text Segmentation for Index Term Identification and Keyphrase Extraction","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-segmentation-by-language-using-minimum","title":"Text Segmentation by Language Using Minimum Description Length","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"topictiling-a-text-segmentation-algorithm","title":"TopicTiling: A Text Segmentation Algorithm based on LDA","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"how-text-segmentation-algorithms-gain-from","title":"How Text Segmentation Algorithms Gain from Topic Models","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"inforex-a-web-based-tool-for-text-corpus","title":"Inforex -- a web-based tool for text corpus management and semantic annotation","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-layer-discourse-annotation-of-a-dutch","title":"Multi-Layer Discourse Annotation of a Dutch Text Corpus","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"5c6ffc1b324591d036c636e6864368eaebaf2e028ad5ae14705e7b801b4b9173","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}