{"id":"https://openalex.org/W2018078808","doi":"https://doi.org/10.1145/1227850.1227852","title":"Using data mining techniques and rough set theory for language modeling","display_name":"Using data mining techniques and rough set theory for language modeling","publication_year":2007,"publication_date":"2007-04-01","ids":{"openalex":"https://openalex.org/W2018078808","doi":"https://doi.org/10.1145/1227850.1227852","mag":"2018078808"},"language":"en","primary_location":{"id":"doi:10.1145/1227850.1227852","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1227850.1227852","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"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 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/A5002094141","display_name":"Yong Chen","orcid":"https://orcid.org/0000-0002-9820-1614"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["University of Hong Kong, The 54th Research Institute of CTE, China and Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong, The 54th Research Institute of CTE, China and Fudan University","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113663825","display_name":"Kwok-Ping Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kwok-Ping Chan","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3682,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62657011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":"1","first_page":"2","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9797999858856201,"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":0.8367810845375061},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7591471672058105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.652725338935852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6438776850700378},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6084343194961548},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5499942302703857},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5386699438095093},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5212750434875488},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5166264176368713},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43489694595336914},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4208322763442993},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3778645992279053},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14554086327552795},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09170776605606079},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08182337880134583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8367810845375061},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7591471672058105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.652725338935852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6438776850700378},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6084343194961548},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5499942302703857},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5386699438095093},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5212750434875488},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5166264176368713},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43489694595336914},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4208322763442993},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3778645992279053},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14554086327552795},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09170776605606079},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08182337880134583},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1227850.1227852","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1227850.1227852","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"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 Language Information Processing","raw_type":"journal-article"},{"id":"pmh:oai:hub.hku.hk:10722/89180","is_oa":false,"landing_page_url":"http://hdl.handle.net/10722/89180","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1505790639","https://openalex.org/W1901876417","https://openalex.org/W1997362234","https://openalex.org/W2091614382","https://openalex.org/W2115495120","https://openalex.org/W2132984323","https://openalex.org/W2148194215","https://openalex.org/W2166559705","https://openalex.org/W2243440996","https://openalex.org/W2916336495","https://openalex.org/W4229735753","https://openalex.org/W4255833381"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2944691285","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3],"propose":[4],"a":[5,13,34],"new":[6],"postprocessing":[7],"strategy,":[8,27],"word":[9,15,25,48,90],"suggestion,":[10],"based":[11],"on":[12],"multiple":[14,47],"trigger-pair":[16,49],"language":[17],"model":[18],"for":[19],"Chinese":[20,28],"character":[21,29],"recognizers.":[22],"With":[23],"the":[24,39,46,58,70,87],"suggestion":[26],"recognizers":[30],"may":[31],"even":[32],"achieve":[33],"recognition":[35,42],"rate":[36],"greater":[37],"than":[38],"top-n":[40],"candidate":[41],"rate.":[43],"To":[44],"construct":[45],"model,":[50],"data":[51],"mining":[52],"techniques":[53],"are":[54],"used":[55,68],"to":[56,72,81],"alleviate":[57],"intensive":[59],"computation":[60],"problem.":[61],"Furthermore,":[62],"rough":[63],"set":[64],"theory":[65],"is":[66],"first":[67],"in":[69,79,86],"study":[71],"discover":[73],"negatively":[74],"correlated":[75],"relationships":[76],"between":[77],"words":[78,85],"order":[80],"prevent":[82],"introducing":[83],"wrong":[84],"process":[88],"of":[89],"suggestion.":[91]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}