{"id":"https://openalex.org/W2012946874","doi":"https://doi.org/10.3115/1119250.1119261","title":"A Chinese efficient analyser integrating word segmentation, part-of-speech tagging, partial parsing and full parsing","display_name":"A Chinese efficient analyser integrating word segmentation, part-of-speech tagging, partial parsing and full parsing","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2012946874","doi":"https://doi.org/10.3115/1119250.1119261","mag":"2012946874"},"language":"en","primary_location":{"id":"doi:10.3115/1119250.1119261","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119261","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119261","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/10.3115/1119250.1119261","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012794465","display_name":"Guodong Zhou","orcid":"https://orcid.org/0000-0002-7887-5099"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"GuoDong Zhou","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Inst. for Infocomm Res., Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Inst. for Infocomm Res., Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101860993","display_name":"Jian Su","orcid":"https://orcid.org/0009-0001-9484-5885"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jian Su","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Inst. for Infocomm Res., Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Inst. for Infocomm Res., Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012794465"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":1.8727,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87517341,"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":"78","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9922000169754028,"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":0.9868000149726868,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.870246171951294},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8224998712539673},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8006038665771484},{"id":"https://openalex.org/keywords/analyser","display_name":"Analyser","score":0.698819637298584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5638027191162109},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.531001091003418},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5293432474136353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5224639177322388},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.48987290263175964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4842076301574707},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.436376690864563},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43189889192581177},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13518869876861572},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.07946670055389404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.870246171951294},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8224998712539673},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8006038665771484},{"id":"https://openalex.org/C26834552","wikidata":"https://www.wikidata.org/wiki/Q3275846","display_name":"Analyser","level":2,"score":0.698819637298584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5638027191162109},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.531001091003418},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5293432474136353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5224639177322388},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.48987290263175964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4842076301574707},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.436376690864563},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43189889192581177},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13518869876861572},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.07946670055389404},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1119250.1119261","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119261","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119261","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:10.1.1.75.6890","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.6890","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/ZhouSu.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1119250.1119261","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119261","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119261","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2012946874.pdf","grobid_xml":"https://content.openalex.org/works/W2012946874.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1499641710","https://openalex.org/W1986543644","https://openalex.org/W1991133427","https://openalex.org/W2051721519","https://openalex.org/W2087165009","https://openalex.org/W2088970556","https://openalex.org/W2098921539","https://openalex.org/W2125838338","https://openalex.org/W2165112885","https://openalex.org/W2788296320"],"related_works":["https://openalex.org/W1904432136","https://openalex.org/W2039934116","https://openalex.org/W1987186610","https://openalex.org/W2096369514","https://openalex.org/W2005457983","https://openalex.org/W2092836002","https://openalex.org/W1975208120","https://openalex.org/W2047029026","https://openalex.org/W2116938113","https://openalex.org/W2095908250"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"an":[3,37],"efficient":[4,26],"analyser":[5,27],"for":[6,137],"the":[7,43,48,57,66,71,83,88,101,105,110,128,138],"Chinese":[8,25,139],"language,":[9],"which":[10],"efficiently":[11],"and":[12,21,36,69,85],"effectively":[13],"integrates":[14],"word":[15],"segmentation,":[16],"part-of-speech":[17],"tagging,":[18],"partial":[19],"parsing":[20],"full":[22],"parsing.":[23],"The":[24],"is":[28,61,76,79],"based":[29,46],"on":[30,47],"a":[31,93,121],"Hidden":[32],"Markov":[33],"Model":[34],"(HMM)":[35],"HMM-based":[38,50],"tagger.":[39],"That":[40],"is,":[41],"all":[42,104,127],"components":[44,106,129],"are":[45],"same":[49,58],"tagging":[51],"engine.":[52,123],"One":[53],"advantage":[54,75],"of":[55,103,112,117],"using":[56],"single":[59,122],"engine":[60],"that":[62,77,126],"it":[63,78],"largely":[64],"decreases":[65],"code":[67,84],"size":[68],"makes":[70],"maintenance":[72],"easy.":[73],"Another":[74],"easy":[80],"to":[81,120],"optimise":[82],"thus":[86],"improve":[87],"speed":[89,91],"while":[90],"plays":[92],"critical":[94],"important":[95],"role":[96],"in":[97],"many":[98],"applications.":[99],"Finally,":[100],"performances":[102,133],"can":[107,130],"benefit":[108],"from":[109],"optimisation":[111],"existing":[113],"algorithms":[114,119],"and/or":[115],"adoption":[116],"better":[118],"Experiments":[124],"show":[125],"achieve":[131],"state-of-art":[132],"with":[134],"high":[135],"efficiency":[136],"language.":[140]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}