{"id":"https://openalex.org/W2166987457","doi":"https://doi.org/10.1145/2184436.2184440","title":"Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation","display_name":"Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2166987457","doi":"https://doi.org/10.1145/2184436.2184440","mag":"2166987457"},"language":"en","primary_location":{"id":"doi:10.1145/2184436.2184440","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2184436.2184440","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/A5065145414","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0001-5910-1568"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015785439","display_name":"Chengqing Zong","orcid":"https://orcid.org/0000-0002-9864-3818"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengqing Zong","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070399630","display_name":"Keh\u2010Yih Su","orcid":"https://orcid.org/0000-0003-2838-1362"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keh-Yih Su","raw_affiliation_strings":["Behavior Design Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Behavior Design Corporation","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7843,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.950403,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"11","issue":"2","first_page":"1","last_page":"41"},"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":0.9993000030517578,"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":0.9908999800682068,"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/discriminative-model","display_name":"Discriminative model","score":0.8418521881103516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8212641477584839},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7252634167671204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6909815669059753},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.615010142326355},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5966922640800476},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5966415405273438},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5824216604232788},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5045424699783325},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4973743259906769},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4491101801395416},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4470163583755493},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.42476147413253784},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42185649275779724},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3562723398208618},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3304887115955353},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11178174614906311},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08913829922676086}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8418521881103516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212641477584839},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7252634167671204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6909815669059753},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.615010142326355},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5966922640800476},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5966415405273438},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5824216604232788},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5045424699783325},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4973743259906769},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4491101801395416},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4470163583755493},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.42476147413253784},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42185649275779724},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3562723398208618},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3304887115955353},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11178174614906311},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08913829922676086},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2184436.2184440","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2184436.2184440","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7099999785423279,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3941931581","display_name":null,"funder_award_id":"6.10E+15","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W4952878","https://openalex.org/W25062297","https://openalex.org/W44506435","https://openalex.org/W102334056","https://openalex.org/W157259314","https://openalex.org/W222053410","https://openalex.org/W300553845","https://openalex.org/W1506806321","https://openalex.org/W1512811194","https://openalex.org/W1575907248","https://openalex.org/W1631260214","https://openalex.org/W1663973292","https://openalex.org/W1971678616","https://openalex.org/W1979145089","https://openalex.org/W1982498087","https://openalex.org/W1997129315","https://openalex.org/W2008652694","https://openalex.org/W2010576059","https://openalex.org/W2032585622","https://openalex.org/W2036516910","https://openalex.org/W2040786972","https://openalex.org/W2056250865","https://openalex.org/W2086846715","https://openalex.org/W2096175520","https://openalex.org/W2097927681","https://openalex.org/W2102301788","https://openalex.org/W2104820387","https://openalex.org/W2105908356","https://openalex.org/W2107060372","https://openalex.org/W2108220507","https://openalex.org/W2110974939","https://openalex.org/W2113242163","https://openalex.org/W2116983617","https://openalex.org/W2117364574","https://openalex.org/W2124121064","https://openalex.org/W2132961219","https://openalex.org/W2140016149","https://openalex.org/W2140103187","https://openalex.org/W2147880316","https://openalex.org/W2156346614","https://openalex.org/W2158195707","https://openalex.org/W2159406587","https://openalex.org/W2160097208","https://openalex.org/W2163377725","https://openalex.org/W2163568299","https://openalex.org/W2163614729","https://openalex.org/W2165209288","https://openalex.org/W2165664509","https://openalex.org/W2166473218","https://openalex.org/W2170469979","https://openalex.org/W2171849160","https://openalex.org/W2172943974","https://openalex.org/W2181844119","https://openalex.org/W2217873082","https://openalex.org/W2233994034","https://openalex.org/W2405762604","https://openalex.org/W2467575451","https://openalex.org/W2489487449","https://openalex.org/W2598654328","https://openalex.org/W2741609678","https://openalex.org/W2755930238","https://openalex.org/W2787323337","https://openalex.org/W2787623005","https://openalex.org/W2791379569","https://openalex.org/W2892737606","https://openalex.org/W2964327378","https://openalex.org/W3145501851","https://openalex.org/W6683955732"],"related_works":["https://openalex.org/W2987280934","https://openalex.org/W2093104230","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W2113687551","https://openalex.org/W4386184937","https://openalex.org/W2751624083","https://openalex.org/W4241564561"],"abstract_inverted_index":{"Among":[0],"statistical":[1],"approaches":[2,25,70,94,180],"to":[3,61,74,142,163,204,215,240],"Chinese":[4],"word":[5],"segmentation,":[6],"the":[7,15,27,35,47,51,75,83,102,144,147,151,159,178,183,199,213,221],"word-based":[8,99],"n-gram":[9],"(":[10,18],"generative":[11,117,148,153],")":[12,20],"model":[13,21,84,141,154,162,214],"and":[14,82,110,188,230,238],"character-based":[16,93,138,160],"tagging":[17],"discriminative":[19,111,161],"are":[22,95,113],"two":[23,69],"dominant":[24],"in":[26,182,243],"literature.":[28,184],"The":[29],"former":[30],"gives":[31],"excellent":[32],"performance":[33,64],"for":[34,56,65],"in-vocabulary":[36],"(IV)":[37],"words;":[38],"however,":[39],"it":[40,59],"handles":[41],"out-of-vocabulary":[42],"(OOV)":[43],"words":[44],"poorly.":[45],"On":[46],"other":[48],"hand,":[49],"though":[50],"latter":[52],"is":[53,106,155,192,202,209,225,236],"more":[54,96,114],"robust":[55,97,115],"OOV":[57],"words,":[58],"fails":[60],"deliver":[62],"satisfactory":[63],"IV":[66],"words.":[67],"These":[68],"behave":[71],"differently":[72],"due":[73],"unit":[76],"they":[77,86,120],"use":[78],"(word":[79],"vs.":[80,89],"character)":[81],"form":[85],"adopt":[87],"(generative":[88],"discriminative).":[90],"In":[91],"general,":[92],"than":[98,116],"ones,":[100,118],"as":[101,130],"vocabulary":[103],"of":[104,126,146,166,198],"characters":[105],"a":[107,137,186,195,231],"closed":[108],"set;":[109],"models":[112],"since":[119],"can":[121],"flexibly":[122],"include":[123],"all":[124,177],"kinds":[125],"available":[127],"information,":[128],"such":[129],"future":[131],"context.":[132],"This":[133],"article":[134],"first":[135],"proposes":[136],"n":[139],"-gram":[140],"enhance":[143],"robustness":[145],"approach.":[149],"Then":[150],"proposed":[152,222,237],"further":[156,216],"integrated":[157,174,223],"with":[158],"take":[164],"advantage":[165],"both":[167],"approaches.":[168],"Our":[169],"experiments":[170],"show":[171],"that":[172],"this":[173],"approach":[175,224],"outperforms":[176],"existing":[179],"reported":[181],"Afterwards,":[185],"complete":[187],"detailed":[189],"error":[190],"analysis":[191],"conducted.":[193],"Since":[194],"significant":[196],"portion":[197],"critical":[200],"errors":[201],"related":[203],"numerical/foreign":[205],"strings,":[206],"character-type":[207],"information":[208],"then":[210],"incorporated":[211],"into":[212],"improve":[217],"its":[218],"performance.":[219],"Last,":[220],"tested":[226],"on":[227],"cross-domain":[228],"corpora,":[229],"semi-supervised":[232],"domain":[233],"adaptation":[234],"algorithm":[235],"shown":[239],"be":[241],"effective":[242],"our":[244],"experiments.":[245]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}