{"id":"https://openalex.org/W3009619352","doi":"https://doi.org/10.1145/3359990","title":"Isarn Dharma Word Segmentation Using a Statistical Approach with Named Entity Recognition","display_name":"Isarn Dharma Word Segmentation Using a Statistical Approach with Named Entity Recognition","publication_year":2020,"publication_date":"2020-02-22","ids":{"openalex":"https://openalex.org/W3009619352","doi":"https://doi.org/10.1145/3359990","mag":"3009619352"},"language":"en","primary_location":{"id":"doi:10.1145/3359990","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3359990","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/A5043054558","display_name":"Sittichai Somsap","orcid":null},"institutions":[{"id":"https://openalex.org/I179193067","display_name":"Khon Kaen University","ror":"https://ror.org/03cq4gr50","country_code":"TH","type":"education","lineage":["https://openalex.org/I179193067"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Sittichai Somsap","raw_affiliation_strings":["Natural Language and Speech Processing Laboratory (NLSP), Khon Kaen University, Khon Kaen, Thailand"],"affiliations":[{"raw_affiliation_string":"Natural Language and Speech Processing Laboratory (NLSP), Khon Kaen University, Khon Kaen, Thailand","institution_ids":["https://openalex.org/I179193067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008878621","display_name":"Pusadee Seresangtakul","orcid":"https://orcid.org/0000-0001-7579-2485"},"institutions":[{"id":"https://openalex.org/I179193067","display_name":"Khon Kaen University","ror":"https://ror.org/03cq4gr50","country_code":"TH","type":"education","lineage":["https://openalex.org/I179193067"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Pusadee Seresangtakul","raw_affiliation_strings":["Natural Language and Speech Processing Laboratory (NLSP), Khon Kaen University, Khon Kaen, Thailand"],"affiliations":[{"raw_affiliation_string":"Natural Language and Speech Processing Laboratory (NLSP), Khon Kaen University, Khon Kaen, Thailand","institution_ids":["https://openalex.org/I179193067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043054558"],"corresponding_institution_ids":["https://openalex.org/I179193067"],"apc_list":null,"apc_paid":null,"fwci":0.7954,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77552287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"19","issue":"2","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/dharma","display_name":"Dharma","score":0.7720557451248169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6990768909454346},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6867767572402954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6787462830543518},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6780203580856323},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.660062849521637},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5795819163322449},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5405541658401489},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.48049724102020264},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42940765619277954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3533632755279541},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2496974766254425}],"concepts":[{"id":"https://openalex.org/C2777168331","wikidata":"https://www.wikidata.org/wiki/Q134293","display_name":"Dharma","level":3,"score":0.7720557451248169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6990768909454346},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6867767572402954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6787462830543518},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6780203580856323},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.660062849521637},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5795819163322449},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5405541658401489},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.48049724102020264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42940765619277954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3533632755279541},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2496974766254425},{"id":"https://openalex.org/C75699723","wikidata":"https://www.wikidata.org/wiki/Q748","display_name":"Buddhism","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3359990","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3359990","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":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322335","display_name":"Khon Kaen University","ror":"https://ror.org/03cq4gr50"},{"id":"https://openalex.org/F4320337278","display_name":"Faculty of Science, Prince of Songkla University","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W163000676","https://openalex.org/W205209790","https://openalex.org/W1486819475","https://openalex.org/W1992367715","https://openalex.org/W1997455322","https://openalex.org/W2088233541","https://openalex.org/W2093014948","https://openalex.org/W2108387313","https://openalex.org/W2136528950","https://openalex.org/W2145269183","https://openalex.org/W2166987457","https://openalex.org/W2330805959","https://openalex.org/W2398978578","https://openalex.org/W2513992500","https://openalex.org/W2598684926","https://openalex.org/W3010392501","https://openalex.org/W4246499047","https://openalex.org/W6712408168"],"related_works":["https://openalex.org/W4392255232","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","https://openalex.org/W2159591557","https://openalex.org/W2058548953"],"abstract_inverted_index":{"In":[0,138,159],"this":[1],"study,":[2],"we":[3,65,161],"developed":[4,66],"an":[5,67,204],"Isarn":[6,25,29,68],"Dharma":[7,26,30,69],"word":[8,17,21,35,108,151,168],"segmentation":[9,169],"system.":[10],"We":[11],"mainly":[12],"focused":[13],"on":[14,134,153],"solving":[15],"the":[16,39,57,81,99,107,115,129,135,146,154,163,176,183,187,192,195,199,210],"ambiguity":[18],"and":[19,54,75,77,89,101,157],"unknown":[20,124],"problems":[22],"in":[23,34,56],"unsegmented":[24],"text.":[27,60],"Ambiguous":[28],"words":[31,46,125],"occur":[32],"frequently":[33],"construction":[36,155],"due":[37],"to":[38,105,118,144],"writing":[40,59],"style":[41],"without":[42],"tone":[43],"markers.":[44],"Thus,":[45],"can":[47],"be":[48],"interpreted":[49],"as":[50],"having":[51],"different":[52],"tones":[53],"meanings":[55],"same":[58],"To":[61],"overcome":[62],"these":[63],"problems,":[64],"character":[70,136],"cluster\u2013(IDCC)":[71],"based":[72,133,152],"statistical":[73,87,103,112,131],"model":[74,88,113],"affixation":[76,90],"integrated":[78],"it":[79],"with":[80,91,166],"named":[82,92],"entity":[83,93],"recognition":[84,94],"method":[85,97,165,178,197],"(IDCC-C-based":[86],"(NER)).":[95],"This":[96],"integrates":[98],"IDCC-based":[100,111],"character-based":[102,130],"models":[104],"distinguish":[106],"boundaries.":[109],"The":[110,123,171],"utilizes":[114],"IDCC":[116,211],"feature":[117],"disambiguate":[119],"any":[120],"ambiguous":[121],"words.":[122],"are":[126],"handled":[127],"using":[128],"model,":[132],"features.":[137],"addition,":[139],"linguistic":[140],"knowledge":[141],"is":[142],"employed":[143],"detect":[145],"boundaries":[147],"of":[148,202],"a":[149],"new":[150],"morphology":[156],"NER.":[158],"evaluations,":[160],"compared":[162],"proposed":[164,177,196],"various":[167],"methods.":[170],"experimental":[172],"results":[173],"showed":[174],"that":[175,206],"performed":[179],"slightly":[180],"better":[181,208],"than":[182,209],"other":[184],"methods":[185],"when":[186],"corpus":[188],"size":[189],"increased.":[190],"Using":[191],"test":[193],"set,":[194],"obtained":[198],"best":[200],"F-measure":[201,205],"92.19,":[203],"was":[207],"longest":[212],"matching":[213],"grouping":[214],"at":[215],"2.85.":[216]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}