{"id":"https://openalex.org/W3134349173","doi":"https://doi.org/10.1145/3409488","title":"Optimisation of the Largest Annotated Tibetan Corpus Combining Rule-based, Memory-based, and Deep-learning Methods","display_name":"Optimisation of the Largest Annotated Tibetan Corpus Combining Rule-based, Memory-based, and Deep-learning Methods","publication_year":2021,"publication_date":"2021-01-31","ids":{"openalex":"https://openalex.org/W3134349173","doi":"https://doi.org/10.1145/3409488","mag":"3134349173"},"language":"en","primary_location":{"id":"doi:10.1145/3409488","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3409488","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3409488","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","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3409488","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037929993","display_name":"Marieke Meelen","orcid":"https://orcid.org/0000-0003-0395-8372"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marieke Meelen","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073253549","display_name":"\u00c9lie Roux","orcid":"https://orcid.org/0000-0002-3787-8226"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u00c9lie Roux","raw_affiliation_strings":["BDRC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BDRC","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005588276","display_name":"Nathan W. Hill","orcid":"https://orcid.org/0000-0001-6423-017X"},"institutions":[{"id":"https://openalex.org/I124357947","display_name":"University of London","ror":"https://ror.org/04cw6st05","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947"]},{"id":"https://openalex.org/I31575130","display_name":"SOAS University of London","ror":"https://ror.org/04vrxay34","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I31575130"]},{"id":"https://openalex.org/I4210160447","display_name":"Universidad de Londres","ror":"https://ror.org/054v4yq51","country_code":"MX","type":"education","lineage":["https://openalex.org/I4210160447"]}],"countries":["GB","MX"],"is_corresponding":false,"raw_author_name":"Nathan Hill","raw_affiliation_strings":["SOAS, University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SOAS, University of London","institution_ids":["https://openalex.org/I31575130","https://openalex.org/I124357947","https://openalex.org/I4210160447"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3648,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83857503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"1","first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9872000217437744,"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/pipeline","display_name":"Pipeline (software)","score":0.8189694881439209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7914872765541077},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6362659335136414},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6052823662757874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5889427065849304},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5460852980613708},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42377984523773193},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.393587589263916},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21665793657302856}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8189694881439209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914872765541077},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6362659335136414},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6052823662757874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5889427065849304},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5460852980613708},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42377984523773193},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.393587589263916},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21665793657302856},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3409488","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3409488","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3409488","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"},{"id":"pmh:oai:eprints.soas.ac.uk:34903","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402168","display_name":"SOAS Research Online (SOAS University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31575130","host_organization_name":"SOAS University of London","host_organization_lineage":["https://openalex.org/I31575130"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:oai:tara.tcd.ie:2262/102695","is_oa":true,"landing_page_url":"http://hdl.handle.net/2262/102695","pdf_url":"https://www.tara.tcd.ie/bitstreams/a792d942-04f8-4021-8b03-16e6088dd6d7/download","source":{"id":"https://openalex.org/S4306400387","display_name":"Trinity's Access to Research Output (TARA) (Trinity College Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205274468","host_organization_name":"Trinity College Dublin","host_organization_lineage":["https://openalex.org/I205274468"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/310506","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/310506","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.17863/cam.57600","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.57600","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.1145/3409488","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3409488","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3409488","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7099999785423279,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1943662601","display_name":"Beyond Boundaries: Religion, Region, Language and the State","funder_award_id":"609823","funder_id":"https://openalex.org/F4320338352","funder_display_name":"FP7 Ideas: European Research Council"},{"id":"https://openalex.org/G5492190018","display_name":null,"funder_award_id":"PF170063","funder_id":"https://openalex.org/F4320320004","funder_display_name":"British Academy"}],"funders":[{"id":"https://openalex.org/F4320315711","display_name":"Hill's Pet Nutrition","ror":null},{"id":"https://openalex.org/F4320320004","display_name":"British Academy","ror":"https://ror.org/0302b4677"},{"id":"https://openalex.org/F4320338352","display_name":"FP7 Ideas: European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3134349173.pdf","grobid_xml":"https://content.openalex.org/works/W3134349173.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1490593707","https://openalex.org/W1964643440","https://openalex.org/W2124680313","https://openalex.org/W2493916176","https://openalex.org/W2786173426","https://openalex.org/W2952352518","https://openalex.org/W2972412515","https://openalex.org/W2989208677","https://openalex.org/W4236703367","https://openalex.org/W4247896594","https://openalex.org/W4394042916"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W3037187668","https://openalex.org/W2611989081","https://openalex.org/W4234772502","https://openalex.org/W2731899572","https://openalex.org/W2380685755","https://openalex.org/W4230611425","https://openalex.org/W4294635752","https://openalex.org/W4304166257","https://openalex.org/W2252100032"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3,17,47,71,100],"pipeline":[4,26,89],"that":[5],"converts":[6],"collections":[7],"of":[8,32,52,62,74,79,85,90,108],"Tibetan":[9,56,109],"documents":[10],"in":[11,46],"plain":[12],"text":[13],"or":[14],"XML":[15],"into":[16],"fully":[18],"segmented":[19],"and":[20,49,65,106],"POS-tagged":[21],"corpus.":[22],"We":[23],"apply":[24],"the":[25,28,33,53,60,97],"to":[27,58,76,95],"large":[29],"extent":[30],"collection":[31],"Buddhist":[34],"Digital":[35],"Resource":[36],"Center.":[37],"The":[38,82],"semi-supervised":[39],"methods":[40,67],"presented":[41],"here":[42],"not":[43],"only":[44],"result":[45],"new":[48],"improved":[50],"version":[51],"largest":[54],"annotated":[55],"corpus":[57,99],"date,":[59],"integration":[61],"rule-based,":[63],"memory-based,":[64],"neural-network":[66],"also":[68],"serves":[69],"as":[70],"good":[72],"example":[73],"how":[75],"overcome":[77],"challenges":[78],"under-researched":[80],"languages.":[81],"end-to-end":[83],"accuracy":[84],"our":[86],"entire":[87],"automatic":[88],"91.99%":[91],"is":[92],"high":[93],"enough":[94],"make":[96],"resulting":[98],"useful":[101],"resource":[102],"for":[103],"both":[104],"linguists":[105],"scholars":[107],"studies.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
