{"id":"https://openalex.org/W2140016149","doi":"https://doi.org/10.1162/089120105775299177","title":"Chinese Word Segmentation and Named Entity Recognition: A Pragmatic Approach","display_name":"Chinese Word Segmentation and Named Entity Recognition: A Pragmatic Approach","publication_year":2005,"publication_date":"2005-12-01","ids":{"openalex":"https://openalex.org/W2140016149","doi":"https://doi.org/10.1162/089120105775299177","mag":"2140016149"},"language":"en","primary_location":{"id":"doi:10.1162/089120105775299177","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120105775299177","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120105775299177","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/10.1162/089120105775299177","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research Asia, Natural Language Computing Group, Microsoft Research Asia, 5F, Sigma Center, No. 49, Zhichun Road, Beijing, 100080, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Natural Language Computing Group, Microsoft Research Asia, 5F, Sigma Center, No. 49, Zhichun Road, Beijing, 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399461","display_name":"Mu Li","orcid":"https://orcid.org/0000-0002-4433-2301"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mu Li","raw_affiliation_strings":["Microsoft Research Asia, Natural Language Computing Group, Microsoft Research Asia, 5F, Sigma Center, No. 49, Zhichun Road, Beijing, 100080, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Natural Language Computing Group, Microsoft Research Asia, 5F, Sigma Center, No. 49, Zhichun Road, Beijing, 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066941389","display_name":"Changning Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang-Ning Huang","raw_affiliation_strings":["Microsoft Research Asia, Natural Language Computing Group, Microsoft Research Asia, 5F, Sigma Center, No. 49, Zhichun Road, Beijing, 100080, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Natural Language Computing Group, Microsoft Research Asia, 5F, Sigma Center, No. 49, Zhichun Road, Beijing, 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112730666","display_name":"Andi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138040","display_name":"Velocity Clinical Research (United States)","ror":"https://ror.org/04nh35860","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andi Wu","raw_affiliation_strings":["GrapeCity Inc"],"affiliations":[{"raw_affiliation_string":"GrapeCity Inc","institution_ids":["https://openalex.org/I4210138040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114910293"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":17.8111,"has_fulltext":true,"cited_by_count":221,"citation_normalized_percentile":{"value":0.99222908,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"31","issue":"4","first_page":"531","last_page":"574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9904000163078308,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8567513227462769},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7301705479621887},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6671521067619324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6204891204833984},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6037915349006653},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5622724890708923},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5535844564437866},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.499981164932251},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.43059250712394714},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2522512674331665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8567513227462769},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7301705479621887},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6671521067619324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6204891204833984},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6037915349006653},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5622724890708923},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5535844564437866},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.499981164932251},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.43059250712394714},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2522512674331665},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/089120105775299177","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120105775299177","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120105775299177","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:10.1.1.329.4574","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.4574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology-new/J/J05/J05-4005.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.534.7964","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.534.7964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mt-archive.info/CL-2006-Gao.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.7099","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.7099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/~jfgao/paper/msr-tr-2004-123.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:6204a57d9aaa4652b530bfb949bcb795","is_oa":true,"landing_page_url":"https://doaj.org/article/6204a57d9aaa4652b530bfb949bcb795","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 31, Iss 4 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/089120105775299177","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120105775299177","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120105775299177","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":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2140016149.pdf","grobid_xml":"https://content.openalex.org/works/W2140016149.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W41384227","https://openalex.org/W79835312","https://openalex.org/W114321176","https://openalex.org/W142477701","https://openalex.org/W580098341","https://openalex.org/W581857221","https://openalex.org/W1238390741","https://openalex.org/W1486886935","https://openalex.org/W1491178396","https://openalex.org/W1491745322","https://openalex.org/W1518670641","https://openalex.org/W1540550673","https://openalex.org/W1558333962","https://openalex.org/W1574901103","https://openalex.org/W1604792744","https://openalex.org/W1934041838","https://openalex.org/W1967084801","https://openalex.org/W1973200086","https://openalex.org/W1974967573","https://openalex.org/W1975191211","https://openalex.org/W1979262500","https://openalex.org/W1979557360","https://openalex.org/W1984635093","https://openalex.org/W1996034123","https://openalex.org/W2002160975","https://openalex.org/W2008652694","https://openalex.org/W2027869740","https://openalex.org/W2033295622","https://openalex.org/W2036516910","https://openalex.org/W2036701977","https://openalex.org/W2054882585","https://openalex.org/W2083979457","https://openalex.org/W2086628205","https://openalex.org/W2093476618","https://openalex.org/W2093478938","https://openalex.org/W2096175520","https://openalex.org/W2096301385","https://openalex.org/W2098594428","https://openalex.org/W2099531983","https://openalex.org/W2105518356","https://openalex.org/W2108220507","https://openalex.org/W2113110240","https://openalex.org/W2117400858","https://openalex.org/W2118563017","https://openalex.org/W2127713198","https://openalex.org/W2129287413","https://openalex.org/W2134237567","https://openalex.org/W2138104808","https://openalex.org/W2139565135","https://openalex.org/W2142263282","https://openalex.org/W2146574666","https://openalex.org/W2148603752","https://openalex.org/W2156909104","https://openalex.org/W2158195707","https://openalex.org/W2160842254","https://openalex.org/W2163377725","https://openalex.org/W2164107060","https://openalex.org/W2217873082","https://openalex.org/W2420187884","https://openalex.org/W2578672022","https://openalex.org/W2791279190","https://openalex.org/W2799061466","https://openalex.org/W2951485524","https://openalex.org/W2996160789","https://openalex.org/W4231741839","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3136209078","https://openalex.org/W2147102537","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2058548953","https://openalex.org/W2785359773","https://openalex.org/W2385598138"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3,60,92,112,174,189,218],"pragmatic":[4,61,133,149],"approach":[5,191],"to":[6,131,192,229],"Chinese":[7,26,32,146,157,199],"word":[8,114,158,203,214],"segmentation.":[9],"It":[10,168],"differs":[11],"from":[12],"most":[13],"previous":[14],"approaches":[15,150],"mainly":[16],"in":[17,34,53,64,91,101,154,166],"three":[18],"respects.":[19],"First,":[20],"while":[21],"theoretical":[22],"linguists":[23],"have":[24,151],"defined":[25,38],"words":[27,33,68,72],"using":[28],"various":[29],"linguistic":[30],"criteria,":[31],"this":[35],"study":[36],"are":[37,49,97],"pragmatically":[39],"as":[40],"segmentation":[41,115,128],"units":[42],"whose":[43],"definition":[44],"depends":[45],"on":[46,180,234,249],"how":[47],"they":[48],"used":[50],"and":[51,69,83,187,212,216],"processed":[52],"realistic":[54],"computer":[55],"applications.":[56],"Second,":[57],"we":[58,105,121],"propose":[59],"mathematical":[62],"framework":[63,182],"which":[65,162],"segmenting":[66],"known":[67],"detecting":[70],"unknown":[71],"of":[73,111,126,145,170,183,197,220,227],"different":[74,136,143,230,239],"types":[75],"(i.e.,":[76],"morphologically":[77],"derived":[78],"words,":[79],"factoids,":[80],"named":[81,209],"entities,":[82],"other":[84,102],"unlisted":[85],"words)":[86],"can":[87],"be":[88,164],"performed":[89],"simultaneously":[90],"unified":[93,190],"way.":[94],"These":[95,148],"tasks":[96],"usually":[98],"conducted":[99],"separately":[100],"systems.":[103],"Finally,":[104],"do":[106],"not":[107],"assume":[108],"the":[109,124,132,181,193,225,243,251],"existence":[110],"universal":[113],"standard":[116],"that":[117,135,177,242],"is":[118,178],"application-independent.":[119],"Instead,":[120],"argue":[122],"for":[123,223],"necessity":[125],"multiple":[127],"standards":[129,240],"due":[130],"fact":[134],"natural":[137],"language":[138,200],"processing":[139],"applications":[140],"might":[141],"require":[142],"granularities":[144],"words.":[147],"been":[152],"implemented":[153],"an":[155],"adaptive":[156,244],"segmenter,":[159],"called":[160],"MSRSeg,":[161],"will":[163],"described":[165],"detail.":[167],"consists":[169],"two":[171],"components:":[172],"(1)":[173,228],"generic":[175],"segmenter":[176],"based":[179],"linear":[184],"mixture":[185],"models":[186],"provides":[188],"five":[194,235],"fundamental":[195],"features":[196],"word-level":[198],"processing:":[201],"lexicon":[202],"processing,":[204],"morphological":[205],"analysis,":[206],"factoid":[207],"detection,":[208],"entity":[210],"recognition,":[211],"new":[213],"identification;":[215],"(2)":[217],"set":[219],"output":[221,226],"adaptors":[222],"adapting":[224],"application-specific":[231],"standards.":[232],"Evaluation":[233],"test":[236,252],"sets":[237],"with":[238],"shows":[241],"system":[245],"achieves":[246],"state-of-the-art":[247],"performance":[248],"all":[250],"sets.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}