{"id":"https://openalex.org/W1978623802","doi":"https://doi.org/10.3115/1119250.1119275","title":"A unicode based adaptive segmentor","display_name":"A unicode based adaptive segmentor","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1978623802","doi":"https://doi.org/10.3115/1119250.1119275","mag":"1978623802"},"language":"en","primary_location":{"id":"doi:10.3115/1119250.1119275","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119275","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119275","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second SIGHAN workshop on Chinese language processing  -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119275","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016391596","display_name":"Qin Lu","orcid":"https://orcid.org/0000-0002-9092-2476"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Q. Lu","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hung Hom, Hong Kong","The Hong Kong Polytechnic Univ., Hung Hom, Hong Kong#TAB#"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"The Hong Kong Polytechnic Univ., Hung Hom, Hong Kong#TAB#","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013885426","display_name":"Suk\u2010Tak Chan","orcid":"https://orcid.org/0000-0001-6627-3173"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"S. T. Chan","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hung Hom, Hong Kong","The Hong Kong Polytechnic Univ., Hung Hom, Hong Kong#TAB#"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"The Hong Kong Polytechnic Univ., Hung Hom, Hong Kong#TAB#","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103400868","display_name":"Ruozhou Xu","orcid":"https://orcid.org/0009-0009-4876-1523"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"R. F. Xu","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hung Hom, Hong Kong","The Hong Kong Polytechnic Univ., Hung Hom, Hong Kong#TAB#"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"The Hong Kong Polytechnic Univ., Hung Hom, Hong Kong#TAB#","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034073323","display_name":"Tin-Shing Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"T. S. Chiu","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hung Hom, Hong Kong","The Hong Kong Polytechnic Univ., Hung Hom, Hong Kong#TAB#"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"The Hong Kong Polytechnic Univ., Hung Hom, Hong Kong#TAB#","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031164058","display_name":"Bohan Li","orcid":"https://orcid.org/0000-0002-7837-3953"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"B. L. Li","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052324373","display_name":"Shiwen Yu","orcid":"https://orcid.org/0000-0002-8514-3195"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"S. W. Yu","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016391596"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.4682,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73600666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"17","issue":null,"first_page":"164","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9661999940872192,"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":0.9661999940872192,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9210000038146973,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9150999784469604,"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/unicode","display_name":"Unicode","score":0.8718996047973633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8388930559158325},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.7139024138450623},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6531426906585693},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6518668532371521},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5490629076957703},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.5216922163963318},{"id":"https://openalex.org/keywords/modularity","display_name":"Modularity (biology)","score":0.43687519431114197},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.41510629653930664},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3682253360748291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36594998836517334},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.09877949953079224}],"concepts":[{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.8718996047973633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8388930559158325},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7139024138450623},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6531426906585693},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6518668532371521},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5490629076957703},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.5216922163963318},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.43687519431114197},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.41510629653930664},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3682253360748291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36594998836517334},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.09877949953079224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3115/1119250.1119275","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119275","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119275","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second SIGHAN workshop on Chinese language processing  -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.64.4426","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.64.4426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/W/W03/W03-1725.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.382","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/acl2003/sighan/pdfs/Lu.pdf","raw_type":"text"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/10978","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/10978","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal/Magazine Article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/58312","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/58312","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.3115/1119250.1119275","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119275","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119275","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second SIGHAN workshop on Chinese language processing  -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1978623802.pdf","grobid_xml":"https://content.openalex.org/works/W1978623802.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1218353304"],"related_works":["https://openalex.org/W2297768894","https://openalex.org/W2378076731","https://openalex.org/W2500556566","https://openalex.org/W3109014690","https://openalex.org/W2122405502","https://openalex.org/W2183101619","https://openalex.org/W2114254072","https://openalex.org/W2127721729","https://openalex.org/W2884798239","https://openalex.org/W1531253727"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,55,75],"Unicode":[4],"based":[5],"Chinese":[6,12],"word":[7],"segmentor.":[8],"It":[9],"can":[10],"handle":[11,28],"text":[13],"in":[14,40],"Simplified,":[15],"Traditional,":[16],"or":[17],"mixed":[18],"mode.":[19],"The":[20,44],"system":[21,101],"uses":[22,47],"the":[23,29,41,92,95,100],"strategy":[24],"of":[25,31,94],"divide-and-conquer":[26],"to":[27,50,105],"recognition":[30],"personal":[32],"names,":[33],"numbers,":[34],"time":[35,76],"and":[36,68,80,89,99],"numerical":[37],"values,":[38],"etc":[39],"preprocessing":[42],"stage.":[43],"segmentor":[45,96],"further":[46],"tagging":[48],"information":[49],"work":[51],"on":[52],"disambiguation.":[53],"Adopting":[54],"modular":[56],"design":[57],"approach,":[58],"different":[59,66,106],"functional":[60],"parts":[61],"are":[62],"separately":[63],"implemented":[64],"using":[65],"modules":[67,88],"each":[69],"module":[70],"tackles":[71],"one":[72],"problem":[73],"at":[74],"providing":[77],"more":[78],"flexibility":[79],"extensibility.":[81],"Results":[82],"show":[83],"that":[84],"with":[85],"added":[86],"pre-processing":[87],"accessorial":[90],"modules,":[91],"accuracy":[93],"is":[97,102],"increased":[98],"easily":[103],"adaptive":[104],"applications.":[107]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
