{"id":"https://openalex.org/W1982957697","doi":"https://doi.org/10.4018/jthi.2006010102","title":"The Specification of POS Tagging of the Hong Kong University Cantonese Corpus","display_name":"The Specification of POS Tagging of the Hong Kong University Cantonese Corpus","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W1982957697","doi":"https://doi.org/10.4018/jthi.2006010102","mag":"1982957697"},"language":"en","primary_location":{"id":"doi:10.4018/jthi.2006010102","is_oa":false,"landing_page_url":"https://doi.org/10.4018/jthi.2006010102","pdf_url":null,"source":{"id":"https://openalex.org/S130700065","display_name":"International Journal of Technology and Human Interaction","issn_l":"1548-3908","issn":["1548-3908","1548-3916"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Technology and Human Interaction","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/A5073120704","display_name":"Wong Ping-Wai","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Wong Ping-Wai","raw_affiliation_strings":["The University of Hong Kong, Hong Kong","[The University of Hong Kong, Hong Kong}]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"[The University of Hong Kong, Hong Kong}]","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5073120704"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.08226598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":"1","first_page":"21","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.9783999919891357,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.963699996471405,"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/annotation","display_name":"Annotation","score":0.856293797492981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8002147674560547},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7011436223983765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6878129243850708},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6667129397392273},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5467861294746399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.530493974685669},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.48559898138046265},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44230055809020996},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.44197216629981995},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.43234774470329285},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3926335871219635}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.856293797492981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8002147674560547},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7011436223983765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6878129243850708},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6667129397392273},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5467861294746399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.530493974685669},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.48559898138046265},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44230055809020996},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.44197216629981995},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.43234774470329285},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3926335871219635},{"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:10.4018/jthi.2006010102","is_oa":false,"landing_page_url":"https://doi.org/10.4018/jthi.2006010102","pdf_url":null,"source":{"id":"https://openalex.org/S130700065","display_name":"International Journal of Technology and Human Interaction","issn_l":"1548-3908","issn":["1548-3908","1548-3916"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Technology and Human Interaction","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:igg:jthi00:v:2:y:2006:i:1:p:21-38","is_oa":false,"landing_page_url":"https://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/jthi.2006010102","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3114261385","https://openalex.org/W2917843404","https://openalex.org/W2473907094","https://openalex.org/W3084036048","https://openalex.org/W116351045","https://openalex.org/W1927439458","https://openalex.org/W2611159122","https://openalex.org/W1889898471","https://openalex.org/W1560466321","https://openalex.org/W2741500372"],"abstract_inverted_index":{"The":[0,176],"Hong":[1,179],"Kong":[2,180],"University":[3],"Cantonese":[4,28,171,181,203,216],"Corpus":[5],"was":[6,24,50,90],"collected":[7],"from":[8,149],"transcribed":[9],"spontaneous":[10],"speech":[11],"in":[12,60,99,118,126,161],"conversations":[13],"and":[14,30,111,121,172,217,230],"radio":[15],"programs":[16],"that":[17,115],"involved":[18],"two":[19],"to":[20,163,220,225],"four":[21],"people.":[22],"It":[23],"word-segmented,":[25],"annotated":[26],"with":[27,33,147],"pronunciation,":[29],"recently":[31],"tagged":[32],"word":[34,75,133],"classes":[35,76,134],"by":[36,77,92,139,159,209],"adopting":[37],"the":[38,72,93,100,106,109,113,140,150,165,197,207,226],"parts-of-speech":[39],"(POS)":[40],"scheme":[41],"of":[42,71,95,108,130,142,167,170,178,200,222],"Yu":[43],"et":[44],"al.":[45],"(2002).":[46],"This":[47,102],"scheme,":[48],"which":[49],"designed":[51],"for":[52,68,81,193,214,234],"tagging":[53,61,120,131,169],"written":[54],"Mandarin":[55],"texts,":[56],"encountered":[57,125],"some":[58,79,132],"problems":[59,124],"spoken":[62],"Cantonese.":[63,235],"However,":[64],"it":[65],"is":[66,218],"flexible":[67],"further":[69],"expansion":[70],"26":[73],"basic":[74],"customizing":[78],"subclasses":[80],"annotating":[82],"other":[83,173],"Chinese":[84,174],"dialects":[85],"(e.g.,":[86],"Cantonese).":[87],"Its":[88],"robustness":[89],"proved":[91],"annotation":[94,158],"approximately":[96],"230,000":[97],"words":[98],"HKUCC.":[101],"article":[103],"will":[104,122,135,154],"describe":[105],"format":[107],"corpus":[110,192,213],"provide":[112],"specification":[114],"helps":[116],"annotators":[117],"POS":[119,168],"solve":[123],"manual":[127],"annotation.":[128],"Guidelines":[129],"be":[136,221],"introduced,":[137],"followed":[138],"discussion":[141],"easily":[143],"confused":[144],"tags,":[145],"illustrated":[146],"examples":[148],"corpus.":[151,204],"Further":[152],"work":[153,166,186],"aim":[155],"at":[156],"automatic":[157],"computers":[160],"order":[162],"facilitate":[164],"dialects.":[175],"corpora":[177],"are":[182],"quite":[183],"lacking.":[184],"Past":[185],"focused":[187],"either":[188],"on":[189],"a":[190,211],"POS-tagged":[191,212],"child":[194],"language":[195,232],"or":[196],"phonetic":[198],"transcription":[199],"an":[201],"adult":[202,215],"HKUCC":[205],"fills":[206],"gap":[208],"providing":[210],"believed":[219],"great":[223],"value":[224],"data-driven":[227],"linguistic":[228],"analysis":[229],"natural":[231],"processing":[233]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
