{"id":"https://openalex.org/W3210607400","doi":"https://doi.org/10.1145/3481298","title":"Domain-Aware Word Segmentation for Chinese Language: A Document-Level Context-Aware Model","display_name":"Domain-Aware Word Segmentation for Chinese Language: A Document-Level Context-Aware Model","publication_year":2021,"publication_date":"2021-11-03","ids":{"openalex":"https://openalex.org/W3210607400","doi":"https://doi.org/10.1145/3481298","mag":"3210607400"},"language":"en","primary_location":{"id":"doi:10.1145/3481298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3481298","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","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/A5031577422","display_name":"Kaiyu Huang","orcid":"https://orcid.org/0000-0001-6779-1810"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyu Huang","raw_affiliation_strings":["Dalian University of Technology, Dalian City, Liaoning Province, P. R. C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian City, Liaoning Province, P. R. C","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068405466","display_name":"Keli Xiao","orcid":"https://orcid.org/0000-0001-6494-1174"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keli Xiao","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048033573","display_name":"Fengran Mo","orcid":"https://orcid.org/0000-0002-0838-6994"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengran Mo","raw_affiliation_strings":["Dalian University of Technology, Dalian City, Liaoning Province, P. R. C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian City, Liaoning Province, P. R. C","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051178997","display_name":"Bo Jin","orcid":"https://orcid.org/0000-0002-4094-7499"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Jin","raw_affiliation_strings":["Dalian University of Technology, Dalian City, Liaoning Province, P. R. C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian City, Liaoning Province, P. R. C","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452098","display_name":"Zhuang Liu","orcid":"https://orcid.org/0000-0002-4695-6345"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuang Liu","raw_affiliation_strings":["Dalian University of Technology, Dalian City, Liaoning Province, P. R. C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian City, Liaoning Province, P. R. C","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4210092944"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046871248","display_name":"Degen Huang","orcid":"https://orcid.org/0000-0002-8860-7805"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Degen Huang","raw_affiliation_strings":["Dalian University of Technology, Dalian City, Liaoning Province, P. R. C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian City, Liaoning Province, P. R. C","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4210092944"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6824,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75959627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"21","issue":"2","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11550","display_name":"Text and Document Classification Technologies","score":0.9847000241279602,"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":0.8803645372390747},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6935229897499084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6777002811431885},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6748644113540649},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6526312828063965},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6260252594947815},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.612208902835846},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5730067491531372},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5707119703292847},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5522637963294983},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4705904722213745},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.42518237233161926},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41738998889923096},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3222907781600952},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08032059669494629}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8803645372390747},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6935229897499084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6777002811431885},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6748644113540649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6526312828063965},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6260252594947815},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.612208902835846},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5730067491531372},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5707119703292847},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5522637963294983},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4705904722213745},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.42518237233161926},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41738998889923096},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3222907781600952},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08032059669494629},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3481298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3481298","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G2377133103","display_name":null,"funder_award_id":"U1936109 and 61672127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1516184288","https://openalex.org/W1603598191","https://openalex.org/W1940872118","https://openalex.org/W1966133627","https://openalex.org/W1971678616","https://openalex.org/W2036516910","https://openalex.org/W2137281231","https://openalex.org/W2250739653","https://openalex.org/W2251362855","https://openalex.org/W2252225757","https://openalex.org/W2358307482","https://openalex.org/W2516334389","https://openalex.org/W2613806735","https://openalex.org/W2757350179","https://openalex.org/W2910676115","https://openalex.org/W2930957955","https://openalex.org/W2962885853","https://openalex.org/W2963355640","https://openalex.org/W2964093505","https://openalex.org/W2964352165","https://openalex.org/W2997617958","https://openalex.org/W3145501851","https://openalex.org/W6640362995","https://openalex.org/W6683955732","https://openalex.org/W6758581563"],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W4392255232","https://openalex.org/W2944691285","https://openalex.org/W2978383222","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2785359773"],"abstract_inverted_index":{"Word":[0],"segmentation":[1,62,164],"is":[2,63],"an":[3],"essential":[4],"and":[5,34,52,93,106,110,128],"challenging":[6],"task":[7],"in":[8,42,59,153],"natural":[9],"language":[10,16],"processing,":[11],"especially":[12],"for":[13,25],"the":[14,47,57,66,77,113,123,144,150,162,166,174],"Chinese":[15,26],"due":[17],"to":[18,64,75],"its":[19],"high":[20],"linguistic":[21],"complexity.":[22],"Existing":[23,70],"methods":[24,33,71],"word":[27,61,163],"segmentation,":[28],"including":[29],"statistical":[30],"machine":[31],"learning":[32],"neural":[35],"network":[36],"methods,":[37],"usually":[38],"have":[39],"good":[40],"performance":[41,74,175],"specific":[43],"knowledge":[44],"domains.":[45,99,158],"Given":[46],"increasing":[48],"importance":[49],"of":[50,56,146,176],"interdisciplinary":[51],"cross-domain":[53,60,167],"studies,":[54],"one":[55],"challenges":[58],"handle":[65],"out-of-vocabulary":[67],"(OOV)":[68],"words.":[69],"show":[72],"unsatisfactory":[73],"meet":[76],"practical":[78],"standard.":[79],"To":[80],"this":[81],"end,":[82],"we":[83],"propose":[84],"a":[85,104,107,116],"document-level":[86],"context-aware":[87],"model":[88,109],"that":[89],"can":[90,172],"automatically":[91],"perceive":[92],"identify":[94],"OOV":[95,177],"words":[96,178],"from":[97,138,156],"different":[98,139,157],"Our":[100],"method":[101,125,148,171],"jointly":[102],"implements":[103],"word-based":[105],"character-based":[108],"then":[111],"processes":[112],"results":[114,142],"with":[115],"newly":[117],"proposed":[118,170],"reconstruction":[119],"model.":[120],"We":[121],"evaluate":[122],"new":[124],"by":[126],"designing":[127],"conducting":[129],"comprehensive":[130],"experiments":[131],"on":[132],"two":[133],"real-world":[134],"datasets":[135],"(e.g.,":[136],"news":[137],"domains).":[140],"The":[141],"demonstrate":[143],"superiority":[145],"our":[147,169],"over":[149],"state-of-the-art":[151],"models":[152],"handling":[154],"texts":[155],"Importantly,":[159],"when":[160],"doing":[161],"under":[165],"scenario,":[168],"improve":[173],"recognition.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}