{"id":"https://openalex.org/W2030110175","doi":"https://doi.org/10.1142/s0219427907001676","title":"Chunk Segmentation of Chinese Sentences Using a Combined Statistical and Rule-based Approach (CSRA)","display_name":"Chunk Segmentation of Chinese Sentences Using a Combined Statistical and Rule-based Approach (CSRA)","publication_year":2007,"publication_date":"2007-06-01","ids":{"openalex":"https://openalex.org/W2030110175","doi":"https://doi.org/10.1142/s0219427907001676","mag":"2030110175"},"language":"en","primary_location":{"id":"doi:10.1142/s0219427907001676","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427907001676","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","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/A5103135659","display_name":"Rongbo Wang","orcid":"https://orcid.org/0000-0003-1637-2004"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"RONGBO WANG","raw_affiliation_strings":["Institute of Computer Application Technology, School of Computer and Software Engineering, Hangzhou Dianzi University, Xiasha Higher Education Park, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Application Technology, School of Computer and Software Engineering, Hangzhou Dianzi University, Xiasha Higher Education Park, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115591361","display_name":"Xiaohua Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XIAOHUA WANG","raw_affiliation_strings":["Institute of Computer Application Technology, School of Computer and Software Engineering, Hangzhou Dianzi University, Xiasha Higher Education Park, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Application Technology, School of Computer and Software Engineering, Hangzhou Dianzi University, Xiasha Higher Education Park, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051205016","display_name":"Zhiqun Chen","orcid":"https://orcid.org/0000-0001-7103-2024"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ZHIQUN CHEN","raw_affiliation_strings":["Institute of Computer Application Technology, School of Computer and Software Engineering, Hangzhou Dianzi University, Xiasha Higher Education Park, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Application Technology, School of Computer and Software Engineering, Hangzhou Dianzi University, Xiasha Higher Education Park, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050364086","display_name":"Zheru Chi","orcid":"https://orcid.org/0000-0003-0714-8713"},"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":"ZHERU CHI","raw_affiliation_strings":["Center for Multimedia Signal Processing, Department of Electronic and Information Engineering, The Hong kong Polytechnic University, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Multimedia Signal Processing, Department of Electronic and Information Engineering, The Hong kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08788287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":"02n03","first_page":"197","last_page":"218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9958999752998352,"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":0.9958999752998352,"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":0.9710999727249146,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9372000098228455,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9021847248077393},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7417377829551697},{"id":"https://openalex.org/keywords/collocation","display_name":"Collocation (remote sensing)","score":0.7411280274391174},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7073410749435425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6998663544654846},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6863166093826294},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5590761303901672},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5218554735183716},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46479886770248413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17942720651626587},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09373986721038818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9021847248077393},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7417377829551697},{"id":"https://openalex.org/C80023036","wikidata":"https://www.wikidata.org/wiki/Q5147531","display_name":"Collocation (remote sensing)","level":2,"score":0.7411280274391174},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7073410749435425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6998663544654846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6863166093826294},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5590761303901672},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5218554735183716},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46479886770248413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17942720651626587},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09373986721038818},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219427907001676","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427907001676","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","raw_type":"journal-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/10292","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/10292","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W99935078","https://openalex.org/W2097125878","https://openalex.org/W2099008367","https://openalex.org/W2099942883","https://openalex.org/W2110190189","https://openalex.org/W2118655449","https://openalex.org/W2329627532","https://openalex.org/W2349722316","https://openalex.org/W2360615260","https://openalex.org/W2363036475","https://openalex.org/W2368598057","https://openalex.org/W2375192328","https://openalex.org/W2376034920","https://openalex.org/W2392593357","https://openalex.org/W3207352138"],"related_works":["https://openalex.org/W2362350383","https://openalex.org/W2095908250","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2785359773","https://openalex.org/W2058548953","https://openalex.org/W2385598138"],"abstract_inverted_index":{"Deep":[0],"parsing":[1,32],"of":[2,24,33],"Chinese":[3,25,34],"sentences":[4,35],"is":[5,28,79],"a":[6,49,54,75,82],"very":[7],"challenging":[8],"task":[9],"due":[10],"to":[11,29],"their":[12],"complexity":[13],"such":[14,102],"as":[15,103],"ambiguous":[16],"word":[17],"boundaries":[18],"and":[19,57,93,106],"meanings.":[20],"An":[21],"alternative":[22],"mode":[23],"language":[26],"processing":[27],"perform":[30],"shallow":[31],"in":[36],"which":[37,78],"chunk":[38,50,66,96,104,107],"segmentation":[39,51,67,97],"plays":[40],"an":[41],"important":[42],"role.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"present":[48],"algorithm":[52],"using":[53],"combined":[55],"statistical":[56,76],"rule-based":[58],"approach":[59],"(CSRA).":[60],"The":[61],"decision":[62],"rules":[63],"for":[64,99],"refining":[65],"are":[68],"generated":[69],"from":[70,74],"incorrectly":[71],"segmented":[72],"chunks":[73],"model":[77],"built":[80],"on":[81],"training":[83],"corpus.":[84],"Experimental":[85],"results":[86,98],"show":[87],"that":[88],"the":[89],"CSRA":[90],"works":[91],"well":[92],"produces":[94],"satisfactory":[95],"subsequent":[100],"processes":[101],"tagging":[105],"collocation":[108],"extraction.":[109]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
