{"id":"https://openalex.org/W2154748198","doi":"https://doi.org/10.1017/s1351324901002637","title":"Compound noun segmentation based on lexical data extracted from corpus","display_name":"Compound noun segmentation based on lexical data extracted from corpus","publication_year":2001,"publication_date":"2001-06-01","ids":{"openalex":"https://openalex.org/W2154748198","doi":"https://doi.org/10.1017/s1351324901002637","mag":"2154748198"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324901002637","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324901002637","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","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/A5061768302","display_name":"Juntae Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"JUNTAE YOON","raw_affiliation_strings":["IRCS, University of Pennsylvania, 3401 Walnut St., Suite 400A, Philadelphia, PA 19104-6228, USA; e-mail:","IRCS, University of Pennsylvania, 3401 Walnut St., Suite 400A, Philadelphia, PA 19104-6228, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRCS, University of Pennsylvania, 3401 Walnut St., Suite 400A, Philadelphia, PA 19104-6228, USA; e-mail:","institution_ids":["https://openalex.org/I922845939"]},{"raw_affiliation_string":"IRCS, University of Pennsylvania, 3401 Walnut St., Suite 400A, Philadelphia, PA 19104-6228, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061768302"],"corresponding_institution_ids":["https://openalex.org/I79576946","https://openalex.org/I922845939"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.14116799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"7","issue":"2","first_page":"167","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9930999875068665,"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":0.9778000116348267,"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":0.852647066116333},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8199436068534851},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.80305016040802},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.785843014717102},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6999512910842896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.666692852973938},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.43602675199508667},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4359123110771179},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36127498745918274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3367273211479187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.852647066116333},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8199436068534851},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.80305016040802},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.785843014717102},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6999512910842896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.666692852973938},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.43602675199508667},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4359123110771179},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36127498745918274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3367273211479187},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324901002637","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324901002637","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1523444292","https://openalex.org/W1970961429","https://openalex.org/W2002089154","https://openalex.org/W2015201047","https://openalex.org/W2040540444","https://openalex.org/W2049755725","https://openalex.org/W2076042735","https://openalex.org/W2115390146","https://openalex.org/W2912565176"],"related_works":["https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2095908250","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2785359773","https://openalex.org/W2058548953","https://openalex.org/W2362013696"],"abstract_inverted_index":{"Compound":[0],"noun":[1,45],"segmentation":[2,46,56,83],"is":[3,90,110],"one":[4],"of":[5,16,42,58,129],"the":[6],"crucial":[7],"problems":[8],"in":[9,18,24,100],"Korean":[10,19,43],"language":[11],"processing":[12],"because":[13],"a":[14,53,64,82,88,101,124],"series":[15],"nouns":[17,72,94],"may":[20],"appear":[21],"without":[22],"space":[23],"real":[25],"text,":[26],"which":[27,73,132],"makes":[28],"it":[29,62],"difficult":[30],"to":[31,69,135],"identify":[32],"its":[33],"morphological":[34],"constituents.":[35],"This":[36],"paper":[37],"presents":[38],"an":[39,78],"effective":[40,126],"method":[41],"compound":[44,71],"based":[47,112],"on":[48,113],"lexical":[49],"data":[50,86],"extracted":[51],"from":[52,87],"corpus.":[54],"The":[55,108],"consists":[57],"two":[59],"tasks:":[60],"First,":[61],"uses":[63],"Hand-Build":[65],"Segmentation":[66],"Dictionary":[67,104],"(HBSD)":[68],"segment":[70],"frequently":[74],"occur":[75],"or":[76],"need":[77],"exceptional":[79],"process.":[80],"Second,":[81],"algorithm":[84],"using":[85,117],"corpus":[89],"proposed,":[91],"where":[92],"simple":[93],"and":[95],"their":[96],"frequencies":[97],"are":[98],"stored":[99],"Simple":[102],"Noun":[103],"(SND)":[105],"for":[106],"segmentation.":[107],"analysis":[109],"executed":[111],"modified":[114],"tabular":[115],"parsing":[116],"min-max":[118],"operation.":[119],"Our":[120],"experiments":[121],"have":[122],"shown":[123],"very":[125,137],"accuracy":[127],"rate":[128],"about":[130],"97.29%,":[131],"turns":[133],"out":[134],"be":[136],"effective.":[138]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}