{"id":"https://openalex.org/W2420187884","doi":"https://doi.org/10.1162/089120100561746","title":"A Compression-based Algorithm for Chinese Word Segmentation","display_name":"A Compression-based Algorithm for Chinese Word Segmentation","publication_year":2000,"publication_date":"2000-09-01","ids":{"openalex":"https://openalex.org/W2420187884","doi":"https://doi.org/10.1162/089120100561746","mag":"2420187884"},"language":"en","primary_location":{"id":"doi:10.1162/089120100561746","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120100561746","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120100561746","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120100561746","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025875274","display_name":"William J. Teahan","orcid":"https://orcid.org/0000-0003-3640-6750"},"institutions":[{"id":"https://openalex.org/I522815984","display_name":"Robert Gordon University","ror":"https://ror.org/04f0qj703","country_code":"GB","type":"education","lineage":["https://openalex.org/I522815984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"W. J. Teahan","raw_affiliation_strings":["The Robert Gordon University, School of Computing and Mathematical Sciences, The Robert Gordon University, Aberdeen, Scotland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Robert Gordon University, School of Computing and Mathematical Sciences, The Robert Gordon University, Aberdeen, Scotland","institution_ids":["https://openalex.org/I522815984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008721062","display_name":"Yingying Wen","orcid":"https://orcid.org/0000-0001-7469-4066"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yingying Wen","raw_affiliation_strings":["University of Waikato, Computer Science, University of Waikato, Hamilton, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waikato, Computer Science, University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027787842","display_name":"Rodger J. McNab","orcid":null},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Rodger McNab","raw_affiliation_strings":["University of Waikato, Computer Science, University of Waikato, Hamilton, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waikato, Computer Science, University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045934263","display_name":"Ian H. Witten","orcid":"https://orcid.org/0000-0001-6428-8988"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Ian H. Witten","raw_affiliation_strings":["University of Waikato, Computer Science, University of Waikato, Hamilton, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waikato, Computer Science, University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.3006,"has_fulltext":true,"cited_by_count":157,"citation_normalized_percentile":{"value":0.99115677,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"26","issue":"3","first_page":"375","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9592000246047974,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8769932985305786},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.7857290506362915},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7613943815231323},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7293953895568848},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6499173641204834},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6286400556564331},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.62474125623703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5835035443305969},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5613789558410645},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.48384490609169006},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4651049077510834},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4377005100250244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4143002927303314},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14371079206466675},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07473605871200562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8769932985305786},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.7857290506362915},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7613943815231323},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7293953895568848},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6499173641204834},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6286400556564331},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.62474125623703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5835035443305969},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5613789558410645},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.48384490609169006},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4651049077510834},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4377005100250244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4143002927303314},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14371079206466675},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07473605871200562},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1162/089120100561746","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120100561746","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120100561746","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.16.1275","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.16.1275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.waikato.ac.nz/~ihw/papers/00WT-YW-RMN-IHW-Comprsbased.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.9340","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.9340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/J/J00/J00-3004.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.5306","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.5306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.waikato.ac.nz/~say1/pubs/teahanCL2000.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.419.4559","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.419.4559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.waikato.ac.nz/~ihw/papers/00WJT-YYW-RJM-IHW-Chinese.pdf","raw_type":"text"},{"id":"pmh:oai:acl.sr.language-archives.org:J00-3004","is_oa":false,"landing_page_url":"http://www.aclweb.org/anthology/J00-3004","pdf_url":null,"source":{"id":"https://openalex.org/S4306402137","display_name":"The COCOON platform (University of Paris)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102197404","host_organization_name":"Universit\u00e9 Paris-Sud","host_organization_lineage":["https://openalex.org/I102197404"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"pmh:oai:doaj.org/article:1443468aa48f475eb37cff25b457665e","is_oa":false,"landing_page_url":"https://doaj.org/article/1443468aa48f475eb37cff25b457665e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 26, Iss 3 (2021)","raw_type":"article"},{"id":"pmh:oai:researchcommons.waikato.ac.nz:10289/1042","is_oa":false,"landing_page_url":"https://hdl.handle.net/10289/1042","pdf_url":null,"source":{"id":"https://openalex.org/S4306400944","display_name":"Research Commons (University of Waikato)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I52179390","host_organization_name":"University of Waikato","host_organization_lineage":["https://openalex.org/I52179390"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Working Paper"}],"best_oa_location":{"id":"doi:10.1162/089120100561746","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120100561746","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120100561746","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2420187884.pdf","grobid_xml":"https://content.openalex.org/works/W2420187884.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W183965307","https://openalex.org/W1492896593","https://openalex.org/W1514078281","https://openalex.org/W1540912880","https://openalex.org/W1558333962","https://openalex.org/W1571468614","https://openalex.org/W1601068932","https://openalex.org/W1907578970","https://openalex.org/W1973200086","https://openalex.org/W1979262500","https://openalex.org/W2001738676","https://openalex.org/W2007780422","https://openalex.org/W2023205579","https://openalex.org/W2045628429","https://openalex.org/W2045644823","https://openalex.org/W2117400858","https://openalex.org/W2125838338","https://openalex.org/W2129287413","https://openalex.org/W2152797116","https://openalex.org/W2160484851","https://openalex.org/W2161628678","https://openalex.org/W2171319769","https://openalex.org/W2217873082","https://openalex.org/W2611071497","https://openalex.org/W2621280964","https://openalex.org/W2752885492","https://openalex.org/W2911331535","https://openalex.org/W4231741839","https://openalex.org/W4248788344"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W2349635380","https://openalex.org/W2353819554","https://openalex.org/W2359488321","https://openalex.org/W1967080779","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"Chinese":[0,118],"is":[1,24,40,75,81],"written":[2],"without":[3],"using":[4,69],"spaces":[5],"or":[6],"other":[7],"word":[8,67,96],"delimiters.":[9],"Although":[10],"a":[11,18,33,36,60,84],"text":[12,34,78],"may":[13],"be":[14],"thought":[15],"of":[16,21,30,38,86],"as":[17,35,99],"corresponding":[19],"sequence":[20,37],"words,":[22],"there":[23],"considerable":[25],"ambiguity":[26],"in":[27,77],"the":[28,102],"placement":[29],"boundaries.":[31],"Interpreting":[32],"words":[39],"beneficial":[41],"for":[42,49,66,117],"some":[43],"information":[44],"retrieval":[45],"and":[46,55,89,107],"storage":[47],"tasks:":[48],"example,":[50],"full-text":[51],"search,":[52],"word-based":[53],"compression,":[54],"keyphrase":[56],"extraction.":[57],"We":[58],"describe":[59],"scheme":[61],"that":[62,74],"infers":[63],"appropriate":[64],"positions":[65],"boundaries":[68,97],"an":[70],"adaptive":[71],"language":[72,119],"model":[73],"standard":[76],"compression.":[79],"It":[80],"trained":[82],"on":[83],"corpus":[85],"presegmented":[87],"text,":[88,94],"when":[90],"applied":[91],"to":[92,100,114],"new":[93],"interpolates":[95],"so":[98],"maximize":[101],"compression":[103],"obtained.":[104],"This":[105],"simple":[106],"general":[108],"method":[109],"performs":[110],"well":[111],"with":[112],"respect":[113],"specialized":[115],"schemes":[116],"segmentation.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}