{"id":"https://openalex.org/W2358307482","doi":null,"title":"Chinese Word Segmentation: A Decade Review","display_name":"Chinese Word Segmentation: A Decade Review","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2358307482","mag":"2358307482"},"language":"en","primary_location":{"id":"mag:2358307482","doi":null,"is_oa":false,"landing_page_url":"https://en.cnki.com.cn/Article_en/CJFDTOTAL-MESS200703001.htm","pdf_url":null,"source":{"id":"https://openalex.org/S2765077740","display_name":"Zhongwen xinxi xuebao","issn_l":"1003-0077","issn":["1003-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4366716320","host_organization_name":"Beijing Institute of Information Engineering","host_organization_lineage":["https://openalex.org/P4366716320"],"host_organization_lineage_names":["Beijing Institute of Information Engineering"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Zhongwen xinxi xuebao","raw_type":null},"volume":null,"type":"review","is_traditional":true,"indexed_in":[],"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/A5100457332","display_name":"Hai  Yan Zhao","orcid":"https://orcid.org/0000-0002-3392-2584","observed_orcids":["https://orcid.org/0000-0002-3392-2584","https://orcid.org/0000-0001-7290-0487"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Hai Zhao","raw_affiliation_strings":["City University of Hong Kong , Hong Kong , China"],"raw_orcid":"https://orcid.org/0000-0002-3392-2584","affiliations":[{"raw_affiliation_string":"City University of Hong Kong , Hong Kong , China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100457332"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":1.2687,"has_fulltext":false,"cited_by_count":136,"citation_normalized_percentile":{"value":0.71052632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0005000000237487257,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/chinese-word-segmentation","display_name":"Chinese word segmentation","score":1.0},{"id":"https://openalex.org/keywords/out-of-vocabulary-words","display_name":"out-of-vocabulary words","score":0.8069999814033508},{"id":"https://openalex.org/keywords/statistical-word-segmentation","display_name":"statistical word segmentation","score":0.6110000014305115},{"id":"https://openalex.org/keywords/vocabulary","display_name":"vocabulary","score":0.7490000128746033},{"id":"https://openalex.org/keywords/lexical-ambiguity","display_name":"lexical ambiguity","score":0.48899999260902405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8720166683197021},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.6944655776023865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6524635553359985},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6364720463752747},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6164376139640808},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6052960753440857},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5773543119430542},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5612418055534363},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.535087525844574},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4689445197582245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44204533100128174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3266258239746094},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0872175395488739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":"mag:2358307482","doi":null,"is_oa":false,"landing_page_url":"https://en.cnki.com.cn/Article_en/CJFDTOTAL-MESS200703001.htm","pdf_url":null,"source":{"id":"https://openalex.org/S2765077740","display_name":"Zhongwen xinxi xuebao","issn_l":"1003-0077","issn":["1003-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4366716320","host_organization_name":"Beijing Institute of Information Engineering","host_organization_lineage":["https://openalex.org/P4366716320"],"host_organization_lineage_names":["Beijing Institute of Information Engineering"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Zhongwen xinxi xuebao","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7100176336","https://openalex.org/W2787623005","https://openalex.org/W2163450644","https://openalex.org/W2172629291","https://openalex.org/W1967541735","https://openalex.org/W2252264945","https://openalex.org/W6939210673","https://openalex.org/W3142655802","https://openalex.org/W2381397648","https://openalex.org/W2397114265"],"abstract_inverted_index":{"During":[0],"the":[1,5,34,68,77,95,101,105,110],"last":[2],"decade,especially":[3],"since":[4],"First":[6],"International":[7],"Chinese":[8,20,37],"Word":[9],"Segmentation":[10],"Bakeoff":[11,73],"was":[12],"held":[13],"in":[14,18,39,70,108],"July":[15],"2003,the":[16],"study":[17],"automatic":[19],"word":[21],"segmentation":[46],"has":[23],"been":[24,43],"greatly":[25],"improved.Those":[26],"improvements":[27],"could":[28],"be":[29],"summarized":[30],"as":[31],"following:(1)":[32],"on":[33],"computation":[35],"sense":[36],"words":[38,83],"real":[40],"text":[41],"have":[42],"well-defined":[44],"by":[45,81],"guidelines":[47],"+":[48,50],"lexicon":[49],"segmented":[51],"corpus;(2)":[52],"practical":[53],"results":[54],"show":[55],"that":[56,63,76,91],"performance":[57,97],"of":[58,64,72,92,98,104,112],"statistic":[59,113],"systems":[61,115],"outperforms":[62,120],"handcrafted":[65],"rule-based":[66],"systems;(3)":[67],"evaluation":[69],"terms":[71],"data":[74],"shows":[75],"accuracy":[78,103,111],"drop":[79],"caused":[80],"outof-vocabulary(OOV)":[82],"is":[84],"at":[85],"least":[86],"five":[87],"times":[88],"greater":[89],"than":[90],"ambiguities;(4)":[94],"better":[96],"OOV":[99],"recognition":[100],"higher":[102],"system":[107],"whole,and":[109],"with":[116],"character-based":[117],"tagging":[118],"approach":[119],"any":[121],"other":[122],"word-based":[123],"system.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":11}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2016-06-24T00:00:00"}
