{"id":"https://openalex.org/W2118822954","doi":"https://doi.org/10.1145/1089815.1089819","title":"Chinese named entity recognition using lexicalized HMMs","display_name":"Chinese named entity recognition using lexicalized HMMs","publication_year":2005,"publication_date":"2005-06-01","ids":{"openalex":"https://openalex.org/W2118822954","doi":"https://doi.org/10.1145/1089815.1089819","mag":"2118822954"},"language":"en","primary_location":{"id":"doi:10.1145/1089815.1089819","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1089815.1089819","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"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 SIGKDD Explorations Newsletter","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/A5101990229","display_name":"Guohong Fu","orcid":"https://orcid.org/0000-0001-6882-6181"},"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":"Guohong Fu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong","[The University of Hong Kong, Hong Kong}]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"[The University of Hong Kong, Hong Kong}]","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045562512","display_name":"Kang Kwong Luke","orcid":"https://orcid.org/0000-0002-2883-3659"},"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":"Kang-Kwong Luke","raw_affiliation_strings":["The University of Hong Kong, Hong Kong","[The University of Hong Kong, Hong Kong}]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"[The University of Hong Kong, Hong Kong}]","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8377,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.87939893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"7","issue":"1","first_page":"19","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11550","display_name":"Text and Document Classification Technologies","score":0.9947999715805054,"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":0.8936580419540405},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.787156343460083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6812286972999573},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6685193777084351},{"id":"https://openalex.org/keywords/lexicalization","display_name":"Lexicalization","score":0.6381317377090454},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6139429211616516},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6128254532814026},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5554813742637634},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5508060455322266},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5097894072532654},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4741246700286865},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4266376793384552},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4244208335876465},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10787433385848999},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.07554134726524353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8936580419540405},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.787156343460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6812286972999573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6685193777084351},{"id":"https://openalex.org/C2777532361","wikidata":"https://www.wikidata.org/wiki/Q687185","display_name":"Lexicalization","level":2,"score":0.6381317377090454},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6139429211616516},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6128254532814026},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5554813742637634},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5508060455322266},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5097894072532654},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4741246700286865},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4266376793384552},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4244208335876465},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10787433385848999},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.07554134726524353},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1089815.1089819","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1089815.1089819","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"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 SIGKDD Explorations Newsletter","raw_type":"journal-article"},{"id":"pmh:oai:hub.hku.hk:10722/54298","is_oa":false,"landing_page_url":"http://hdl.handle.net/10722/54298","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":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W35234968","https://openalex.org/W89503205","https://openalex.org/W287031571","https://openalex.org/W1484305962","https://openalex.org/W1505083828","https://openalex.org/W1511488080","https://openalex.org/W1520377376","https://openalex.org/W1861196058","https://openalex.org/W1967350923","https://openalex.org/W1969886938","https://openalex.org/W1997938337","https://openalex.org/W2009351579","https://openalex.org/W2041614298","https://openalex.org/W2048468185","https://openalex.org/W2081275694","https://openalex.org/W2083979457","https://openalex.org/W2099008367","https://openalex.org/W2117400858","https://openalex.org/W2118936156","https://openalex.org/W2123512824","https://openalex.org/W2155932901","https://openalex.org/W2163377725","https://openalex.org/W3033454065","https://openalex.org/W3145501851","https://openalex.org/W6683955732"],"related_works":["https://openalex.org/W2065474030","https://openalex.org/W3173084154","https://openalex.org/W2982021180","https://openalex.org/W2251497876","https://openalex.org/W2241081188","https://openalex.org/W2128567707","https://openalex.org/W2011383762","https://openalex.org/W2035962958","https://openalex.org/W2250597603","https://openalex.org/W2099896133"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,28,33,44,50,53,70,113,182],"lexicalized":[4,63,144],"HMM-based":[5],"approach":[6],"to":[7,48,65,93,171],"Chinese":[8],"named":[9],"entity":[10,81],"recognition":[11],"(NER).":[12],"To":[13,38],"tackle":[14],"the":[15,61,83,86,96,101,108,115,118,162,176],"problem":[16],"of":[17,35,55,85,110,117],"unknown":[18,22],"words,":[19,57],"we":[20,41],"unify":[21],"word":[23,69],"identification":[24],"and":[25,58,82,100,129,172],"NER":[26,106,149],"as":[27],"single":[29],"tagging":[30,160,163,180],"task":[31],"on":[32,165],"sequence":[34,54],"known":[36,56,68],"words.":[37],"do":[39],"this,":[40],"first":[42],"employ":[43],"known-word":[45,178],"bigram-based":[46],"model":[47],"segment":[49],"sentence":[51],"into":[52],"then":[59],"apply":[60],"uniformly":[62],"HMMs":[64,145],"assign":[66],"each":[67],"proper":[71],"hybrid":[72],"tag":[73],"that":[74,143,158],"indicates":[75],"its":[76,125],"pattern":[77],"in":[78,127],"forming":[79],"an":[80],"category":[84],"formed":[87],"entity.":[88],"Our":[89],"system":[90,119,135],"is":[91,169,185],"able":[92],"integrate":[94],"both":[95],"internal":[97],"formation":[98],"patterns":[99],"surrounding":[102],"contextual":[103],"clues":[104],"for":[105],"under":[107],"framework":[109],"HMMs.":[111,153],"As":[112],"result,":[114],"performance":[116,150],"can":[120,146,173],"be":[121],"improved":[122],"without":[123],"losing":[124],"efficiency":[126],"training":[128],"tagging.":[130],"We":[131],"have":[132],"tested":[133],"our":[134],"using":[136],"different":[137],"public":[138],"corpora.":[139],"The":[140,154],"results":[141,155],"show":[142],"substantially":[147],"improve":[148],"over":[151],"standard":[152],"also":[156],"indicate":[157],"character-based":[159],"(viz.":[161],"based":[164,179],"pure":[166],"single-character":[167],"words)":[168],"comparable":[170],"even":[174],"outperform":[175],"relevant":[177],"when":[181],"lexicalization":[183],"technique":[184],"applied.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}