{"id":"https://openalex.org/W4365138365","doi":"https://doi.org/10.1093/llc/fqad016","title":"Automatic sentence segmentation for classical Chinese: <i>The Spring and Autumn Annals</i> as an example","display_name":"Automatic sentence segmentation for classical Chinese: <i>The Spring and Autumn Annals</i> as an example","publication_year":2023,"publication_date":"2023-04-12","ids":{"openalex":"https://openalex.org/W4365138365","doi":"https://doi.org/10.1093/llc/fqad016"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqad016","is_oa":true,"landing_page_url":"https://doi.org/10.1093/llc/fqad016","pdf_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqad016/49871429/fqad016.pdf","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":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqad016/49871429/fqad016.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037513626","display_name":"Wenjie Fan","orcid":"https://orcid.org/0000-0001-7667-2629"},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Fan","raw_affiliation_strings":["College of Information Management, Nanjing Agricultural University , Nanjing, China","Research Center for Humanities and Social Computing, Nanjing Agricultural University , Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7667-2629","affiliations":[{"raw_affiliation_string":"College of Information Management, Nanjing Agricultural University , Nanjing, China","institution_ids":["https://openalex.org/I119454577"]},{"raw_affiliation_string":"Research Center for Humanities and Social Computing, Nanjing Agricultural University , Nanjing, China","institution_ids":["https://openalex.org/I119454577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101788189","display_name":"Dongbo Wang","orcid":"https://orcid.org/0000-0002-9894-9550"},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbo Wang","raw_affiliation_strings":["College of Information Management, Nanjing Agricultural University , Nanjing, China","Research Center for Humanities and Social Computing, Nanjing Agricultural University , Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9894-9550","affiliations":[{"raw_affiliation_string":"College of Information Management, Nanjing Agricultural University , Nanjing, China","institution_ids":["https://openalex.org/I119454577"]},{"raw_affiliation_string":"Research Center for Humanities and Social Computing, Nanjing Agricultural University , Nanjing, China","institution_ids":["https://openalex.org/I119454577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110370687","display_name":"Shuiqing Huang","orcid":"https://orcid.org/0000-0002-1646-9300"},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuiqing Huang","raw_affiliation_strings":["College of Information Management, Nanjing Agricultural University , Nanjing, China","Research Center for Humanities and Social Computing, Nanjing Agricultural University , Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1646-9300","affiliations":[{"raw_affiliation_string":"College of Information Management, Nanjing Agricultural University , Nanjing, China","institution_ids":["https://openalex.org/I119454577"]},{"raw_affiliation_string":"Research Center for Humanities and Social Computing, Nanjing Agricultural University , Nanjing, China","institution_ids":["https://openalex.org/I119454577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5110370687"],"corresponding_institution_ids":["https://openalex.org/I119454577"],"apc_list":{"value":2522,"currency":"GBP","value_usd":3093},"apc_paid":null,"fwci":0.1308,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53602902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"38","issue":"3","first_page":"1067","last_page":"1077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"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":0.9973999857902527,"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":0.9955999851226807,"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":0.9811000227928162,"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/sentence","display_name":"Sentence","score":0.8156386613845825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7354832291603088},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6814703345298767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6589249968528748},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6539278030395508},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5639739632606506},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.526461660861969},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.48129430413246155},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42738786339759827},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27563419938087463}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8156386613845825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354832291603088},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6814703345298767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6589249968528748},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6539278030395508},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5639739632606506},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.526461660861969},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.48129430413246155},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42738786339759827},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27563419938087463},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/llc/fqad016","is_oa":true,"landing_page_url":"https://doi.org/10.1093/llc/fqad016","pdf_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqad016/49871429/fqad016.pdf","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":{"id":"doi:10.1093/llc/fqad016","is_oa":true,"landing_page_url":"https://doi.org/10.1093/llc/fqad016","pdf_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqad016/49871429/fqad016.pdf","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4365138365.pdf"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2370206419","https://openalex.org/W2374181016","https://openalex.org/W2380471323","https://openalex.org/W2389539985","https://openalex.org/W2952370363","https://openalex.org/W3198659451","https://openalex.org/W6987912981"],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W2995082385","https://openalex.org/W4300537970","https://openalex.org/W4301042974"],"abstract_inverted_index":{"Abstract":[0],"There":[1,104],"exists":[2],"no":[3],"sentence":[4,30,40,155,186,204],"boundary":[5],"in":[6,23,109,140,190],"most":[7,151],"classical":[8,38,50,137,184],"Chinese":[9,39,51,138,185],"literature":[10,18,24],"texts.":[11],"Since":[12],"it":[13],"is":[14,130,146,188],"difficult":[15],"to":[16,45,74,148],"read":[17],"of":[19,37,56,65,125,203],"this":[20,110],"kind,":[21],"experts":[22],"or":[25],"linguistics":[26],"would":[27],"segment":[28],"the":[29,35,54,57,76,116,123,126,150],"manually.":[31],"This":[32],"article":[33,111],"explores":[34],"effectiveness":[36],"segmentation":[41,156,205],"method":[42],"so":[43],"as":[44,179],"provide":[46],"a":[47],"reference":[48],"for":[49,154,183],"punctuation.":[52],"On":[53],"basis":[55],"machine":[58,66],"learning":[59,77],"methods,":[60],"we":[61],"chose":[62],"three":[63,96,113],"components":[64],"learning,":[67],"namely":[68],"models,":[69,86,92,94],"tagging":[70,107,160,172],"schemes,":[71],"and":[72,95,112,120,162,195,208],"features,":[73],"compare":[75],"results.":[78],"The":[79,143,167],"models":[80],"include":[81],"conditional":[82],"random":[83],"field":[84],"(CRF)":[85],"long":[87],"short":[88],"term":[89],"memory":[90],"(LSTM)":[91],"BiLSTM\u2013CRF":[93],"Bidirectional":[97],"Encoder":[98],"Representation":[99],"from":[100],"Transformers":[101],"(BERT)":[102],"models.":[103],"are":[105,165,206],"five":[106],"schemes":[108,161,173],"features":[114,164],"including":[115],"statistical":[117],"feature,":[118,178],"Guangyun,":[119],"Fanqie.":[121],"Finally,":[122],"performance":[124],"combined":[127],"feature":[128],"template":[129],"evaluated":[131],"by":[132],"ten-fold":[133],"cross-validation":[134],"on":[135],"four":[136],"texts":[139],"different":[141],"genres.":[142],"SikuBERT":[144],"model":[145,153],"proved":[147],"be":[149],"effective":[152],"at":[157],"present.":[158],"Different":[159],"various":[163],"introduced.":[166],"results":[168],"show":[169],"that":[170],"5-tag-J":[171],"can":[174],"improve":[175],"performance.":[176],"Statistical":[177],"an":[180],"important":[181,201],"clue":[182],"segmentation,":[187],"useful":[189],"related":[191],"tasks,":[192],"but":[193],"Guangyun":[194],"Fanqie":[196],"have":[197],"little":[198],"impact.":[199],"Other":[200],"factors":[202],"genres":[207],"writing":[209],"styles.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}