{"id":"https://openalex.org/W4221002285","doi":"https://doi.org/10.1142/s2717554522500047","title":"Ancient Tibetan Word Segmentation: Dataset and Methods","display_name":"Ancient Tibetan Word Segmentation: Dataset and Methods","publication_year":2021,"publication_date":"2021-09-01","ids":{"openalex":"https://openalex.org/W4221002285","doi":"https://doi.org/10.1142/s2717554522500047"},"language":"en","primary_location":{"id":"doi:10.1142/s2717554522500047","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554522500047","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language 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/A5101518692","display_name":"Bo An","orcid":"https://orcid.org/0000-0003-0805-4268"},"institutions":[{"id":"https://openalex.org/I114218197","display_name":"Chinese Academy of Social Sciences","ror":"https://ror.org/05bxbmy32","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197"]},{"id":"https://openalex.org/I4210115499","display_name":"Institute of Ethnology and Anthropology","ror":"https://ror.org/01sengv47","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210115499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo An","raw_affiliation_strings":["The Institute of Ethnology and Anthropology, Chinese Academy of Social Sciences, Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Ethnology and Anthropology, Chinese Academy of Social Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I114218197","https://openalex.org/I4210115499"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012082714","display_name":"Congjun Long","orcid":null},"institutions":[{"id":"https://openalex.org/I114218197","display_name":"Chinese Academy of Social Sciences","ror":"https://ror.org/05bxbmy32","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197"]},{"id":"https://openalex.org/I4210115499","display_name":"Institute of Ethnology and Anthropology","ror":"https://ror.org/01sengv47","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210115499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congjun Long","raw_affiliation_strings":["The Institute of Ethnology and Anthropology, Chinese Academy of Social Sciences, Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Ethnology and Anthropology, Chinese Academy of Social Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I114218197","https://openalex.org/I4210115499"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21904775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":"03n04","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9952999949455261,"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":0.9952999949455261,"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/T13122","display_name":"Linguistics and Cultural Studies","score":0.9473000168800354,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9290000200271606,"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/segmentation","display_name":"Segmentation","score":0.7939194440841675},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.7021665573120117},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6762007474899292},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6485096216201782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5467202067375183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5353434681892395},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4688495397567749},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4648394286632538},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.30645227432250977},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06818073987960815}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7939194440841675},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.7021665573120117},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6762007474899292},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6485096216201782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5467202067375183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353434681892395},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4688495397567749},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4648394286632538},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30645227432250977},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06818073987960815},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s2717554522500047","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554522500047","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1791508882","https://openalex.org/W1799919711","https://openalex.org/W1963938256","https://openalex.org/W1979285701","https://openalex.org/W1991108267","https://openalex.org/W1998289661","https://openalex.org/W2069598966","https://openalex.org/W2124680313","https://openalex.org/W2138136853","https://openalex.org/W2250739653","https://openalex.org/W2274880506","https://openalex.org/W2757041753","https://openalex.org/W2772987967","https://openalex.org/W2905474383","https://openalex.org/W2921004873","https://openalex.org/W2963077975","https://openalex.org/W3035193825","https://openalex.org/W3100727892","https://openalex.org/W3171942767","https://openalex.org/W4235806404","https://openalex.org/W4242708012"],"related_works":["https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2159591557","https://openalex.org/W2785359773","https://openalex.org/W2058548953","https://openalex.org/W2385598138","https://openalex.org/W2366925922"],"abstract_inverted_index":{"Tibetan":[0,13,21,31,41,53,62,79,102,131],"ancient":[1,12,30,40,52,61,78,101,130],"literature":[2,6],"is":[3],"an":[4],"important":[5],"material":[7],"for":[8,74],"the":[9,17,25,37,60,75,94,98,113,117,127],"study":[10],"of":[11,19,27,39,45,77,100,129],"culture,":[14],"history,":[15],"and":[16,97,123],"development":[18],"Sino":[20],"language":[22],"family.":[23],"However,":[24],"lack":[26],"work":[28],"on":[29,67],"word":[32,63,80,89,103,124,132],"segmentation":[33,64,90,104],"tools":[34],"seriously":[35],"restricts":[36],"research":[38],"literature.":[42],"In":[43],"view":[44],"this":[46,48,68],"situation,":[47],"paper":[49],"first":[50],"utilizes":[51],"interlaced":[54],"contrast":[55],"tagging":[56],"data":[57,122],"to":[58],"extract":[59],"dataset.":[65],"Based":[66],"dataset,":[69],"we":[70],"conduct":[71],"numerous":[72],"experiments":[73],"task":[76],"segmentation.":[81,133],"Experimental":[82],"results":[83,114],"show":[84,115],"that":[85,116],"BiLSTM":[86],"+":[87],"CRF":[88],"algorithm":[91],"can":[92,105],"achieve":[93],"best":[95],"performance,":[96],"performance":[99,128],"be":[106],"further":[107],"improved":[108],"through":[109],"model":[110],"ensemble.":[111],"And":[112],"unknown":[118],"words,":[119],"insufficient":[120],"training":[121],"ambiguity":[125],"restrict":[126]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}