{"id":"https://openalex.org/W2536828412","doi":"https://doi.org/10.1109/nlpke.2011.6138229","title":"Enhancement of unsupervised feature selection for conditional random fields learning in Chinese word segmentation","display_name":"Enhancement of unsupervised feature selection for conditional random fields learning in Chinese word segmentation","publication_year":2011,"publication_date":"2011-11-01","ids":{"openalex":"https://openalex.org/W2536828412","doi":"https://doi.org/10.1109/nlpke.2011.6138229","mag":"2536828412"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2011.6138229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2011.6138229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","raw_type":"proceedings-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/A5065489269","display_name":"Mike Tian-Jian Jiang","orcid":"https://orcid.org/0000-0002-2496-2699"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Mike Tian-Jian Jiang","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119558606","display_name":"Wen\u2212Lian Hsu","orcid":"https://orcid.org/0000-0001-7061-3513"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Lian Hsu","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060820042","display_name":"Chan-Hung Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chan-Hung Kuo","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102138803","display_name":"Ting\u2010Hao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ting-Hao Yang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4396,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77334622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"382","last_page":"389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980000257492065,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9962000250816345,"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/conditional-random-field","display_name":"Conditional random field","score":0.6950644254684448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6631101369857788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5807503461837769},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5688862204551697},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5443021059036255},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5378355979919434},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5285405516624451},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5214363932609558},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48654118180274963},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47329726815223694},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.46391668915748596},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4594780504703522},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4387884736061096},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4093360900878906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3904079794883728},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2509925663471222}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6950644254684448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6631101369857788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5807503461837769},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5688862204551697},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5443021059036255},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5378355979919434},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5285405516624451},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5214363932609558},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48654118180274963},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47329726815223694},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.46391668915748596},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4594780504703522},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4387884736061096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4093360900878906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3904079794883728},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2509925663471222},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nlpke.2011.6138229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2011.6138229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W25062297","https://openalex.org/W114321176","https://openalex.org/W189514790","https://openalex.org/W1503913248","https://openalex.org/W1507749387","https://openalex.org/W1528203680","https://openalex.org/W1605120103","https://openalex.org/W1631260214","https://openalex.org/W1773803948","https://openalex.org/W1831215082","https://openalex.org/W1922658394","https://openalex.org/W1971678616","https://openalex.org/W1975191211","https://openalex.org/W1996034123","https://openalex.org/W2004827279","https://openalex.org/W2033295622","https://openalex.org/W2041412237","https://openalex.org/W2124121064","https://openalex.org/W2137683197","https://openalex.org/W2147707543","https://openalex.org/W2147880316","https://openalex.org/W2151297548","https://openalex.org/W2153822208","https://openalex.org/W2154756108","https://openalex.org/W2158874082","https://openalex.org/W2171924756","https://openalex.org/W2185180606","https://openalex.org/W2252066972","https://openalex.org/W2400932086","https://openalex.org/W2535603471","https://openalex.org/W2794998195","https://openalex.org/W2795147870","https://openalex.org/W3088186095","https://openalex.org/W4285719527","https://openalex.org/W6600965556","https://openalex.org/W6604658464","https://openalex.org/W6607642809","https://openalex.org/W6631724362","https://openalex.org/W6636811518","https://openalex.org/W6637852806","https://openalex.org/W6638672268","https://openalex.org/W6682082992","https://openalex.org/W6682520257","https://openalex.org/W6686562023","https://openalex.org/W6691656781","https://openalex.org/W6713289578","https://openalex.org/W6728297115","https://openalex.org/W6750289545","https://openalex.org/W6750383272"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W3102147106","https://openalex.org/W2347460059","https://openalex.org/W2111726165","https://openalex.org/W3136048405","https://openalex.org/W182104056","https://openalex.org/W2208878950"],"abstract_inverted_index":{"This":[0],"work":[1,129],"proposed":[2],"a":[3,46,60,131],"unified":[4],"view":[5],"of":[6,49,64,88,94,100,136,145,152],"several":[7],"unsupervised":[8],"feature":[9,133,139],"selection":[10,134],"based":[11,35],"on":[12,114],"frequent":[13],"strings":[14],"that":[15,86,141],"improve":[16,91],"conditional":[17],"random":[18],"fields":[19],"(CRF)":[20],"model":[21],"for":[22,147],"Chinese":[23],"word":[24],"segmentation":[25],"(CWS).":[26],"These":[27],"features":[28,90,146],"include":[29],"character-based":[30],"n-gram":[31],"(CNG),":[32],"accessor":[33],"variety":[34],"string":[36],"(AVS),":[37],"term-contributed":[38,42],"frequency":[39],"(TCF),":[40],"and":[41,67,78,103,118,154],"boundary":[43,50],"(TCB),":[44],"with":[45],"specific":[47],"manner":[48],"overlapping.":[51],"For":[52],"the":[53,55,58,68,92,95,137],"experiment,":[54],"baseline":[56,96],"is":[57,71],"6-tag,":[59],"state-of-the-art":[61],"labeling":[62],"scheme":[63],"CRF-based":[65,148],"CWS;":[66],"data":[69],"set":[70],"acquired":[72],"from":[73],"SIGHAN":[74,79],"CWS":[75,80],"bakeoff":[76],"2005":[77],"2010.":[81],"The":[82],"experiment":[83],"results":[84],"show":[85],"all":[87],"those":[89],"performance":[93],"system":[97],"in":[98,150],"terms":[99,151],"recall,":[101],"precision,":[102],"their":[104],"harmonic":[105],"average":[106],"as":[107],"F":[108,153,155],"<sub":[109,122,156],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[110,123,157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sub>":[111],"measure":[112],"score,":[113],"both":[115],"accuracy":[116],"(F)":[117],"out-of-vocabulary":[119],"recognition":[120],"(F":[121],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">OOV</sub>":[124,158],").":[125],"In":[126],"particular,":[127],"this":[128],"presents":[130],"novel":[132],"approach":[135],"compound":[138],"\u201cAVS+TCB\u201d":[140],"outperforms":[142],"other":[143],"types":[144],"CSW":[149],".":[159]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}