{"id":"https://openalex.org/W4387800525","doi":"https://doi.org/10.1093/llc/fqad073","title":"Machine learning and data analysis for word segmentation of classical Chinese poems: illustrations with Tang and Song examples","display_name":"Machine learning and data analysis for word segmentation of classical Chinese poems: illustrations with Tang and Song examples","publication_year":2023,"publication_date":"2023-10-20","ids":{"openalex":"https://openalex.org/W4387800525","doi":"https://doi.org/10.1093/llc/fqad073"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqad073","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqad073","pdf_url":null,"source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","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/A5005169817","display_name":"Chao-Lin Liu","orcid":"https://orcid.org/0000-0002-4093-1497"},"institutions":[{"id":"https://openalex.org/I87354575","display_name":"National Chengchi University","ror":"https://ror.org/03rqk8h36","country_code":"TW","type":"education","lineage":["https://openalex.org/I87354575"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chao-Lin Liu","raw_affiliation_strings":["Department of Computer Science, National Chengchi University , 64 Chih-Nan Road Section 2 , Wen-Shan, Taipei 116011, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-4093-1497","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chengchi University , 64 Chih-Nan Road Section 2 , Wen-Shan, Taipei 116011, Taiwan","institution_ids":["https://openalex.org/I87354575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019092772","display_name":"Wei-Ting Chang","orcid":"https://orcid.org/0000-0002-2916-6085"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Ting Chang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California at Riverside , 900 University Avenue , Riverside, California 92521, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California at Riverside , 900 University Avenue , Riverside, California 92521, United States","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087798962","display_name":"Chang-Ting Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chang-Ting Chu","raw_affiliation_strings":["Department of Electrical Engineering, National Yang Ming Chiao Tung University , 1001 University Road , East, Hsinchu 300093, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Yang Ming Chiao Tung University , 1001 University Road , East, Hsinchu 300093, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087739546","display_name":"Ti-Yong Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I87354575","display_name":"National Chengchi University","ror":"https://ror.org/03rqk8h36","country_code":"TW","type":"education","lineage":["https://openalex.org/I87354575"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ti-Yong Zheng","raw_affiliation_strings":["Department of Computer Science, National Chengchi University , 64 Chih-Nan Road Section 2 , Wen-Shan, Taipei 116011, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chengchi University , 64 Chih-Nan Road Section 2 , Wen-Shan, Taipei 116011, Taiwan","institution_ids":["https://openalex.org/I87354575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005169817"],"corresponding_institution_ids":["https://openalex.org/I87354575"],"apc_list":{"value":2522,"currency":"GBP","value_usd":3093},"apc_paid":null,"fwci":0.1586,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54229165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"39","issue":"1","first_page":"228","last_page":"241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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":0.9929999709129333,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/poetry","display_name":"Poetry","score":0.8918061256408691},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6733378767967224},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6686052083969116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5845944881439209},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5331007242202759},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5310901403427124},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5054051876068115},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5017204284667969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4875618815422058},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.45769578218460083},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.32314980030059814},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23705464601516724},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.17856347560882568},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.13815966248512268}],"concepts":[{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.8918061256408691},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6733378767967224},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6686052083969116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5845944881439209},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5331007242202759},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5310901403427124},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5054051876068115},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5017204284667969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4875618815422058},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.45769578218460083},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.32314980030059814},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23705464601516724},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.17856347560882568},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.13815966248512268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/llc/fqad073","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqad073","pdf_url":null,"source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8357538515","display_name":null,"funder_award_id":"110H124D-03","funder_id":"https://openalex.org/F4320316922","funder_display_name":"National Chengchi University"},{"id":"https://openalex.org/G8542041294","display_name":null,"funder_award_id":"MOST-107-2201-E-004-009-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320316922","display_name":"National Chengchi University","ror":"https://ror.org/03rqk8h36"},{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1574901103","https://openalex.org/W1899784274","https://openalex.org/W1987869189","https://openalex.org/W2082092506","https://openalex.org/W2408754830","https://openalex.org/W2478708596","https://openalex.org/W2570565365","https://openalex.org/W2914767245","https://openalex.org/W2944707049","https://openalex.org/W3010521003","https://openalex.org/W3013876529","https://openalex.org/W3173544627","https://openalex.org/W3209086882","https://openalex.org/W4302310270","https://openalex.org/W6731926205","https://openalex.org/W6775784448"],"related_works":["https://openalex.org/W3185823435","https://openalex.org/W2393940967","https://openalex.org/W2251348789","https://openalex.org/W2159591557","https://openalex.org/W2385598138","https://openalex.org/W2346578824","https://openalex.org/W2366925922","https://openalex.org/W2115592387","https://openalex.org/W2905950556","https://openalex.org/W2112534334"],"abstract_inverted_index":{"Abstract":[0],"Words":[1],"are":[2],"essential":[3],"parts":[4],"for":[5,43,100],"understanding":[6],"classical":[7,16],"Chinese":[8,17,51],"poems.":[9],"We":[10,112],"report":[11],"a":[12,31,41,104],"collection":[13],"of":[14,38,50,75,93,103,109,142,152],"32,399":[15],"poems":[18,29,69,120,147],"that":[19,48,81],"were":[20,59],"annotated":[21,28],"with":[22,61,129],"word":[23],"boundaries.":[24],"Statistics":[25],"about":[26,138],"the":[27,36,44,55,68,82,87,94,101,110,119,127,135,143,153],"support":[30],"few":[32],"heuristic":[33],"experiences,":[34],"including":[35],"patterns":[37],"lines":[39],"and":[40,96,125,145],"practice":[42],"parallel":[45],"structures":[46],"(\u5c0d\u4ed7),":[47],"researchers":[49],"literature":[52],"discuss":[53],"in":[54,121],"literature.":[56],"The":[57],"annotators":[58,83],"affiliated":[60],"two":[62],"universities,":[63],"so":[64],"they":[65],"could":[66],"annotate":[67,118],"as":[70,72],"independently":[71],"possible.":[73],"Results":[74],"an":[76],"inter-rater":[77],"agreement":[78],"study":[79],"indicate":[80],"have":[84,97],"consensus":[85,99],"over":[86],"identified":[88,137],"words":[89],"93":[90],"per":[91,107,140,150],"cent":[92,108,141,151],"time":[95],"perfect":[98],"segmentation":[102],"poem":[105],"42":[106],"time.":[111,154],"applied":[113],"unsupervised":[114],"classification":[115],"methods":[116],"to":[117],"several":[122],"different":[123],"settings,":[124],"evaluated":[126],"results":[128],"human":[130],"annotations.":[131],"Under":[132],"favorable":[133],"conditions,":[134],"classifier":[136],"88":[139],"words,":[144],"segmented":[146],"perfectly":[148],"22":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}
