{"id":"https://openalex.org/W2143731190","doi":"https://doi.org/10.3115/1220175.1220255","title":"Self-organizing \u03b7-gram model for automatic word spacing","display_name":"Self-organizing \u03b7-gram model for automatic word spacing","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2143731190","doi":"https://doi.org/10.3115/1220175.1220255","mag":"2143731190"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220255","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220255","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220255","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220255","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042224699","display_name":"Seong-Bae Park","orcid":"https://orcid.org/0000-0002-6453-0348"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Bae Park","raw_affiliation_strings":["Kyungpook National University, Daegu, Korea","[Kyungpook National University, Daegu, Korea]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyungpook National University, Daegu, Korea","institution_ids":["https://openalex.org/I31419693"]},{"raw_affiliation_string":"[Kyungpook National University, Daegu, Korea]","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086196950","display_name":"Yoon-Shik Tae","orcid":null},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoon-Shik Tae","raw_affiliation_strings":["Kyungpook National University, Daegu, Korea","[Kyungpook National University, Daegu, Korea]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyungpook National University, Daegu, Korea","institution_ids":["https://openalex.org/I31419693"]},{"raw_affiliation_string":"[Kyungpook National University, Daegu, Korea]","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049922299","display_name":"Se\u2010Young Park","orcid":"https://orcid.org/0009-0006-6254-8129"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Se-Young Park","raw_affiliation_strings":["Kyungpook National University, Daegu, Korea","[Kyungpook National University, Daegu, Korea]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyungpook National University, Daegu, Korea","institution_ids":["https://openalex.org/I31419693"]},{"raw_affiliation_string":"[Kyungpook National University, Daegu, Korea]","institution_ids":["https://openalex.org/I31419693"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3988,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85526361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"633","last_page":"640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9714000225067139,"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/T10028","display_name":"Topic Modeling","score":0.9714000225067139,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9606000185012817,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9151999950408936,"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/context","display_name":"Context (archaeology)","score":0.7824256420135498},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628452777862549},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7460759282112122},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.7076205611228943},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.6243049502372742},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5827873945236206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48358792066574097},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4811914563179016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.371252179145813},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15784436464309692}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7824256420135498},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628452777862549},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7460759282112122},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.7076205611228943},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.6243049502372742},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5827873945236206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48358792066574097},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4811914563179016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.371252179145813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15784436464309692},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1220175.1220255","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220255","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220255","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.5884","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.5884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P06/P06-1080.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220255","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220255","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220255","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2143731190.pdf","grobid_xml":"https://content.openalex.org/works/W2143731190.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1576520375","https://openalex.org/W1597533204","https://openalex.org/W1608076529","https://openalex.org/W1994851566","https://openalex.org/W1994920552","https://openalex.org/W1996903695","https://openalex.org/W2097927681","https://openalex.org/W2100229817","https://openalex.org/W2105408267","https://openalex.org/W2111094262","https://openalex.org/W2120850260","https://openalex.org/W2121955615","https://openalex.org/W2124008567","https://openalex.org/W2134237567","https://openalex.org/W2389765421","https://openalex.org/W2950186769","https://openalex.org/W2979502264","https://openalex.org/W2998704965","https://openalex.org/W4206462942","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2787311093","https://openalex.org/W155946694","https://openalex.org/W1555968995","https://openalex.org/W4307474317","https://openalex.org/W2057384730","https://openalex.org/W2147879411","https://openalex.org/W2624072012","https://openalex.org/W2008468404"],"abstract_inverted_index":{"An":[0],"automatic":[1,47],"word":[2,26,48],"spacing":[3,27,49],"is":[4,57,116],"one":[5],"of":[6,22,28,61,100,113,120,136,158],"the":[7,76,80,85,89,101,107,111,121,139,146,155,162],"important":[8],"tasks":[9],"in":[10,25,34,134],"Korean":[11],"language":[12],"processing":[13],"and":[14,138],"information":[15],"retrieval.":[16],"Since":[17],"there":[18,30],"are":[19,31,143],"a":[20,43,59],"number":[21],"confusing":[23],"cases":[24],"Korean,":[29],"some":[32],"mistakes":[33],"many":[35],"texts":[36],"including":[37],"news":[38],"articles.":[39],"This":[40,55,124],"paper":[41],"presents":[42],"high-accurate":[44],"method":[45,56,82],"for":[46],"based":[50],"on":[51],"self-organizing":[52,156],"\u03b7-gram":[53,62,159],"model.":[54,164],"basically":[58],"variant":[60],"model,":[63],"but":[64],"achieves":[65,126],"high":[66,127],"accuracy":[67,128],"by":[68,129,145],"automatically":[69,83],"adapting":[70],"context":[71,78,86,108,115,148],"size.In":[72],"order":[73],"to":[74,118],"find":[75],"optimal":[77],"size,":[79],"proposed":[81],"increases":[84],"size":[87,109],"when":[88,110],"contextual":[90],"distribution":[91,112],"after":[92],"increasing":[93],"it":[94],"dose":[95],"not":[96],"agree":[97],"with":[98],"that":[99,119,154],"current":[102,122],"context.":[103,123],"It":[104],"also":[105],"decreases":[106],"reduced":[114,147],"similar":[117],"approach":[125],"considering":[130],"higher":[131],"dimensional":[132],"data":[133],"case":[135],"necessity,":[137],"increased":[140],"computational":[141],"cost":[142],"compensated":[144],"size.":[149],"The":[150],"experimental":[151],"results":[152],"show":[153],"structure":[157],"model":[160],"enhances":[161],"basic":[163]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}