{"id":"https://openalex.org/W2029234334","doi":"https://doi.org/10.1002/(sici)1097-4571(2000)51:4<340::aid-asi4>3.0.co;2-i","title":"Combination and boundary detection approaches on Chinese indexing","display_name":"Combination and boundary detection approaches on Chinese indexing","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W2029234334","doi":"https://doi.org/10.1002/(sici)1097-4571(2000)51:4<340::aid-asi4>3.0.co;2-i","mag":"2029234334"},"language":"en","primary_location":{"id":"doi:10.1002/(sici)1097-4571(2000)51:4<340::aid-asi4>3.0.co;2-i","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1097-4571(2000)51:4<340::aid-asi4>3.0.co;2-i","pdf_url":null,"source":{"id":"https://openalex.org/S4210220780","display_name":"Journal of the American Society for Information Science","issn_l":"0002-8231","issn":["0002-8231","1097-4571"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086292931","display_name":"Christopher C. Yang","orcid":"https://orcid.org/0000-0001-5463-6926"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Christopher C. Yang","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong","Chinese University of Hong Kong Shatin Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Chinese University of Hong Kong Shatin Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715554","display_name":"Johnny Luk","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Johnny W.K. Luk","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong","Chinese University of Hong Kong Shatin Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Chinese University of Hong Kong Shatin Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039306614","display_name":"Stanley K. Yung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Stanley K. Yung","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong","Chinese University of Hong Kong Shatin Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Chinese University of Hong Kong Shatin Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063067173","display_name":"Jerome Yen","orcid":"https://orcid.org/0000-0001-8541-4437"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jerome Yen","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong","Chinese University of Hong Kong Shatin Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Chinese University of Hong Kong Shatin Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5086292931"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":10.7889,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.9784904,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"51","issue":"4","first_page":"340","last_page":"351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9890000224113464,"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":0.9815999865531921,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8390913009643555},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.7343201041221619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6882098317146301},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6314613819122314},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5552765130996704},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48347145318984985},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4720517098903656},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4705740809440613},{"id":"https://openalex.org/keywords/thesaurus","display_name":"Thesaurus","score":0.433494508266449},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4194784164428711},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.21862471103668213},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18474379181861877},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11653122305870056}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8390913009643555},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.7343201041221619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6882098317146301},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6314613819122314},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5552765130996704},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48347145318984985},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4720517098903656},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4705740809440613},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.433494508266449},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4194784164428711},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.21862471103668213},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18474379181861877},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11653122305870056},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1002/(sici)1097-4571(2000)51:4<340::aid-asi4>3.0.co;2-i","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1097-4571(2000)51:4<340::aid-asi4>3.0.co;2-i","pdf_url":null,"source":{"id":"https://openalex.org/S4210220780","display_name":"Journal of the American Society for Information Science","issn_l":"0002-8231","issn":["0002-8231","1097-4571"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.8593","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.8593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.se.cuhk.edu.hk/~yang/papers/yang2000d.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W168434859","https://openalex.org/W210954981","https://openalex.org/W603935256","https://openalex.org/W1558333962","https://openalex.org/W1970258094","https://openalex.org/W1975051991","https://openalex.org/W1996034123","https://openalex.org/W1998080898","https://openalex.org/W2020498346","https://openalex.org/W2038584908","https://openalex.org/W2051885765","https://openalex.org/W2061374747","https://openalex.org/W2096096861","https://openalex.org/W2101857472","https://openalex.org/W2104039702","https://openalex.org/W2108729336","https://openalex.org/W2129287413","https://openalex.org/W2165345215","https://openalex.org/W2169480034","https://openalex.org/W2198380824","https://openalex.org/W2394847164","https://openalex.org/W2442629089","https://openalex.org/W2996160789","https://openalex.org/W4234507609","https://openalex.org/W4242284207","https://openalex.org/W4290649644","https://openalex.org/W6649460998","https://openalex.org/W6663334656","https://openalex.org/W6676449312","https://openalex.org/W6684353036","https://openalex.org/W6718846556"],"related_works":["https://openalex.org/W66250823","https://openalex.org/W2143638542","https://openalex.org/W1490985947","https://openalex.org/W1706008257","https://openalex.org/W1500647188","https://openalex.org/W2132729900","https://openalex.org/W2019565280","https://openalex.org/W2188505374","https://openalex.org/W4245507074","https://openalex.org/W1965473057"],"abstract_inverted_index":{"Digital":[0,43],"libraries":[1,12,185],"store":[2],"materials":[3],"in":[4,10,73,182,192,211,344],"electronic":[5],"format.":[6],"Research":[7],"and":[8,19,29,34,174,255,309,348,367],"development":[9],"digital":[11,104,139,184],"includes":[13],"content":[14],"creation,":[15],"conversion,":[16],"indexing,":[17,95,167],"organization,":[18],"dissemination.":[20],"The":[21,92,128,178,265,294,352],"key":[22],"technological":[23],"issues":[24],"are":[25,115,186,196,236,319],"how":[26,335],"to":[27,58,119,132,204,270,321,333,369],"search":[28,57],"display":[30],"desired":[31],"selections":[32],"from":[33],"across":[35],"large":[36],"collections":[37],"effectively":[38],"[Schatz":[39],"&":[40],"Chen,":[41],"1996].":[42],"library":[44,105],"research":[45,65],"projects":[46],"(DLI-1)":[47],"sponsored":[48],"by":[49],"NSF/DARPA/NASA":[50],"have":[51],"a":[52,102,124,134,193,232,303,336,370],"common":[53],"theme":[54],"of":[55,83,110,172,234,276,288,312,314,327],"bringing":[56],"the":[59,63,68,74,94,96,98,108,170,189,243,253,279,299,307,310,315,328,342,345],"net,":[60],"which":[61,168],"is":[62,79,86,126,131,152,169,210,330,340],"flagship":[64],"effort":[66],"for":[67,90,263,358],"National":[69],"Information":[70],"Infrastructure":[71],"(NII)":[72],"United":[75],"States.":[76],"A":[77],"repository":[78],"an":[80,87],"indexed":[81],"collection":[82],"objects.":[84],"Indexing":[85],"important":[88],"task":[89],"searching.":[91],"better":[93,97],"searching":[99],"result.":[100],"Developing":[101],"universal":[103],"has":[106,143,201],"been":[107,144],"dream":[109],"many":[111,117],"researchers,":[112],"however,":[113,150],"there":[114,151],"still":[116],"problems":[118],"be":[120,356,365],"solved":[121],"before":[122],"such":[123],"vision":[125],"fulfilled.":[127],"most":[129],"critical":[130],"support":[133],"cross-lingual":[135,175],"retrieval":[136],"or":[137,216,221,360],"multilingual":[138],"library.":[140],"Much":[141],"work":[142,155],"done":[145],"on":[146,156,165,260,302,306],"English":[147,212,215],"information":[148,158,176,262],"retrieval,":[149],"relatively":[153],"less":[154],"Chinese":[157,166,173,183,194,199,337],"retrieval.":[159,177],"In":[160,214,230,248,278],"this":[161,249],"article,":[162,250],"we":[163,251],"focus":[164],"foundation":[171],"smallest":[179,190],"indexing":[180,359],"units":[181,191],"words,":[187],"while":[188,290],"sentence":[195,304],"characters.":[197,247,277],"However,":[198],"text":[200,343],"no":[202],"delimiter":[203],"mark":[205],"word":[206,228],"boundaries":[207,244],"as":[208],"it":[209],"text.":[213],"other":[217],"languages":[218],"using":[219],"Roman":[220],"Greek-based":[222],"orthographies,":[223],"often,":[224],"spacing":[225],"reliably":[226],"indicates":[227],"boundaries.":[229],"Chinese,":[231],"number":[233,275],"characters":[235],"placed":[237],"together":[238],"without":[239],"any":[240],"delimiters":[241],"indicating":[242],"between":[245],"consecutive":[246],"investigate":[252],"combination":[254,266,280],"boundary":[256,295],"detection":[257,296],"approaches":[258],"based":[259,305],"mutual":[261,316],"segmentation.":[264],"approach":[267,281,297],"combines":[268],"n-grams":[269,289],"form":[271],"words":[272,354,363],"with":[273],"more":[274],"Algorithm":[282,291],"1":[283],"does":[284],"not":[285],"allow":[286],"overlapping":[287],"2":[292],"does.":[293],"detects":[298],"segmentation":[300],"points":[301],"values":[308,313],"change":[311],"information.":[317],"Experiments":[318],"conducted":[320],"evaluate":[322],"their":[323],"performances.":[324],"An":[325],"interface":[326],"system":[329],"also":[331],"presented":[332],"show":[334],"web":[338],"page":[339,346],"downloaded,":[341],"filtered,":[347],"segmented":[349,353],"into":[350],"words.":[351],"can":[355,364],"submitted":[357,368],"new":[361],"unknown":[362],"identified":[366],"dictionary.":[371]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}