{"id":"https://openalex.org/W2198517985","doi":"https://doi.org/10.1145/2699940","title":"A Unified Model for Solving the OOV Problem of Chinese Word Segmentation","display_name":"A Unified Model for Solving the OOV Problem of Chinese Word Segmentation","publication_year":2015,"publication_date":"2015-06-12","ids":{"openalex":"https://openalex.org/W2198517985","doi":"https://doi.org/10.1145/2699940","mag":"2198517985"},"language":"en","primary_location":{"id":"doi:10.1145/2699940","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2699940","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"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 and Low-Resource 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/A5100456700","display_name":"Xiaoqing Li","orcid":"https://orcid.org/0000-0001-9458-1288"},"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":"Xiaoqing Li","raw_affiliation_strings":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Keh-yih Su","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4365,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77352327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"14","issue":"3","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.996399998664856,"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/treebank","display_name":"Treebank","score":0.8559526205062866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8245804309844971},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.79017174243927},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6901291608810425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6743230223655701},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6368046998977661},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5513100028038025},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5479854345321655},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5438812375068665},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5294746160507202},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4371159076690674},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.15322110056877136},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08631971478462219},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08178636431694031}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.8559526205062866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8245804309844971},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.79017174243927},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6901291608810425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6743230223655701},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6368046998977661},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5513100028038025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5479854345321655},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5438812375068665},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5294746160507202},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4371159076690674},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.15322110056877136},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08631971478462219},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08178636431694031},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2699940","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2699940","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"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 and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G2204133011","display_name":"\u6c49\u8bed\u591a\u5c42\u6b21\u8bed\u7bc7\u5206\u6790\u7406\u8bba\u65b9\u6cd5\u7814\u7a76\u4e0e\u5e94\u7528","funder_award_id":"61333018","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":63,"referenced_works":["https://openalex.org/W25062297","https://openalex.org/W104176810","https://openalex.org/W128638292","https://openalex.org/W157259314","https://openalex.org/W169290101","https://openalex.org/W790017985","https://openalex.org/W1512811194","https://openalex.org/W1575907248","https://openalex.org/W1631260214","https://openalex.org/W1971678616","https://openalex.org/W1979145089","https://openalex.org/W1982498087","https://openalex.org/W2010576059","https://openalex.org/W2020278455","https://openalex.org/W2036516910","https://openalex.org/W2056250865","https://openalex.org/W2079656678","https://openalex.org/W2083979457","https://openalex.org/W2086846715","https://openalex.org/W2096204319","https://openalex.org/W2104747875","https://openalex.org/W2104820387","https://openalex.org/W2110974939","https://openalex.org/W2116983617","https://openalex.org/W2120661206","https://openalex.org/W2124121064","https://openalex.org/W2126504272","https://openalex.org/W2138360330","https://openalex.org/W2140016149","https://openalex.org/W2145905222","https://openalex.org/W2146574666","https://openalex.org/W2154756108","https://openalex.org/W2158195707","https://openalex.org/W2159406587","https://openalex.org/W2160097208","https://openalex.org/W2160817711","https://openalex.org/W2165209288","https://openalex.org/W2165664509","https://openalex.org/W2166987457","https://openalex.org/W2172943974","https://openalex.org/W2181844119","https://openalex.org/W2184048739","https://openalex.org/W2233994034","https://openalex.org/W2250416721","https://openalex.org/W2250542158","https://openalex.org/W2250747734","https://openalex.org/W2252264945","https://openalex.org/W2358307482","https://openalex.org/W2402385743","https://openalex.org/W2405762604","https://openalex.org/W2467575451","https://openalex.org/W2478258606","https://openalex.org/W2524182563","https://openalex.org/W2597684388","https://openalex.org/W2607403128","https://openalex.org/W2620949368","https://openalex.org/W2733628661","https://openalex.org/W2892737606","https://openalex.org/W2916009164","https://openalex.org/W2917458986","https://openalex.org/W3088186095","https://openalex.org/W4205807230","https://openalex.org/W4210870583"],"related_works":["https://openalex.org/W3142119062","https://openalex.org/W2740662036","https://openalex.org/W159209093","https://openalex.org/W589103562","https://openalex.org/W1991220724","https://openalex.org/W2251234095","https://openalex.org/W131522978","https://openalex.org/W2250768577","https://openalex.org/W4396941953","https://openalex.org/W2987280934"],"abstract_inverted_index":{"This":[0,36],"article":[1,37],"proposes":[2],"a":[3],"unified,":[4],"character-based,":[5],"generative":[6,99],"model":[7,100],"to":[8],"incorporate":[9],"additional":[10,27,135],"resources":[11,138],"for":[12],"solving":[13],"the":[14,40,72,75,97,102,114,123,128],"out-of-vocabulary":[15],"(OOV)":[16],"problem":[17],"of":[18,26,44,55,74],"Chinese":[19,115],"word":[20],"segmentation,":[21],"within":[22],"which":[23,56],"different":[24],"types":[25,43,78],"information":[28,91,136],"can":[29,69],"be":[30],"utilized":[31],"independently":[32],"in":[33,82,127],"corresponding":[34,103],"submodels.":[35],"mainly":[38],"addresses":[39],"following":[41],"three":[42],"OOV:":[45],"unseen":[46],"dictionary":[47],"words,":[48,53],"named":[49],"entities,":[50],"and":[51,113,137],"suffix-derived":[52],"none":[54],"are":[57,139],"handled":[58],"well":[59],"by":[60],"current":[61],"approaches.":[62],"The":[63],"results":[64],"show":[65],"that":[66,89,118],"our":[67,106,119],"approach":[68,121],"effectively":[70],"improve":[71],"performance":[73,125],"first":[76],"two":[77],"with":[79,101],"positive":[80],"interaction":[81],"F-score.":[83],"Additionally,":[84],"we":[85],"also":[86],"analyze":[87],"reason":[88],"suffix":[90],"is":[92],"not":[93],"helpful.":[94],"After":[95],"integrating":[96],"proposed":[98],"discriminative":[104],"approach,":[105],"evaluation":[107],"on":[108,130],"various":[109],"corpora---including":[110],"SIGHAN-2005,":[111],"CIPS-SIGHAN-2010,":[112],"Treebank":[116],"(CTB)---shows":[117],"integrated":[120],"achieves":[122],"best":[124],"reported":[126],"literature":[129],"all":[131],"testing":[132],"sets":[133],"when":[134],"allowed.":[140]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}