{"id":"https://openalex.org/W3140140201","doi":"https://doi.org/10.48550/arxiv.2103.16801","title":"Joint Khmer Word Segmentation and Part-of-Speech Tagging Using Deep Learning","display_name":"Joint Khmer Word Segmentation and Part-of-Speech Tagging Using Deep Learning","publication_year":2021,"publication_date":"2021-03-31","ids":{"openalex":"https://openalex.org/W3140140201","doi":"https://doi.org/10.48550/arxiv.2103.16801","mag":"3140140201"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2103.16801","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.16801","pdf_url":"https://arxiv.org/pdf/2103.16801","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.16801","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088468088","display_name":"Rina Buoy","orcid":"https://orcid.org/0000-0002-6960-4262","observed_orcids":["https://orcid.org/0000-0002-6960-4262"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Buoy, Rina","raw_affiliation_strings":["Techo Startup Center (TSC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Techo Startup Center (TSC)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047659557","display_name":"Nguonly Taing","orcid":"https://orcid.org/0000-0002-3332-9465","observed_orcids":["https://orcid.org/0000-0002-3332-9465"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taing, Nguonly","raw_affiliation_strings":["Techo Startup Center (TSC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Techo Startup Center (TSC)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113937726","display_name":"Sokchea Kor","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86346663","display_name":"Royal University of Phnom Penh","ror":"https://ror.org/05rtvan68","country_code":"KH","type":"education","lineage":["https://openalex.org/I86346663"]}],"countries":["KH"],"is_corresponding":false,"raw_author_name":"Kor, Sokchea","raw_affiliation_strings":["Royal University of Phnom Penh (RUPP)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal University of Phnom Penh (RUPP)","institution_ids":["https://openalex.org/I86346663"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9976000189781189,"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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.00139999995008111,"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/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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/khmer-language","display_name":"Khmer language","score":0.9480000138282776},{"id":"https://openalex.org/keywords/word-segmentation","display_name":"word segmentation","score":0.972000002861023},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":1.0},{"id":"https://openalex.org/keywords/deep-learning","display_name":"deep learning","score":0.5210000276565552}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6932501196861267},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6930365562438965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6644620895385742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6203932166099548},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5967788100242615},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5682908892631531},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5196765065193176},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5113189220428467},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31825608015060425},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.060165226459503174},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.03674539923667908},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2103.16801","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.16801","pdf_url":"https://arxiv.org/pdf/2103.16801","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2103.16801","doi":"https://doi.org/10.48550/arxiv.2103.16801","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.16801","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.16801","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.16801","pdf_url":"https://arxiv.org/pdf/2103.16801","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3140140201.pdf","grobid_xml":"https://content.openalex.org/works/W3140140201.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W182831726","https://openalex.org/W2154840867","https://openalex.org/W2398549619","https://openalex.org/W2794296100","https://openalex.org/W2905027511"],"related_works":["https://openalex.org/W4281707381","https://openalex.org/W7204968453","https://openalex.org/W3199380101","https://openalex.org/W2794296100","https://openalex.org/W2593822684","https://openalex.org/W3045480139","https://openalex.org/W2160097208","https://openalex.org/W2165838547","https://openalex.org/W2725860580","https://openalex.org/W4404041696"],"abstract_inverted_index":{"Khmer":[0,58,119],"text":[1],"is":[2,12,22,32,61,95,132],"written":[3],"from":[4],"left":[5],"to":[6],"right":[7],"with":[8,67,135],"optional":[9],"space.":[10],"Space":[11],"not":[13],"served":[14],"as":[15,40],"a":[16,33,62,81,90],"word":[17,54,68,83,99],"boundary":[18],"but":[19],"instead,":[20],"it":[21],"used":[23],"for":[24,36],"readability":[25],"or":[26],"other":[27],"functional":[28],"purposes.":[29],"Word":[30],"segmentation":[31,69,84,100],"prior":[34],"step":[35],"downstream":[37],"tasks":[38],"such":[39],"part-of-speech":[41],"(POS)":[42],"tagging":[43,50,60,73,87,103],"and":[44,70,85,101,113],"thus,":[45],"the":[46,116,126,129,136],"robustness":[47],"of":[48,74,128],"POS":[49,59,86,102,120,139],"highly":[51],"depends":[52],"on":[53,133],"segmentation.":[55],"The":[56,108,122],"conventional":[57,137],"two-stage":[63,138],"process":[64],"that":[65,98,125],"begins":[66],"then":[71],"actual":[72],"each":[75],"word,":[76],"afterward.":[77],"In":[78],"this":[79],"work,":[80],"joint":[82,130],"approach":[88],"using":[89,115],"single":[91],"deep":[92],"learning":[93],"model":[94,110,131],"proposed":[96,109],"so":[97],"can":[104],"be":[105],"performed":[106],"spontaneously.":[107],"was":[111],"trained":[112],"tested":[114],"publicly":[117],"available":[118],"dataset.":[121],"validation":[123],"suggested":[124],"performance":[127],"par":[134],"tagging.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-04-13T00:00:00"}