{"id":"https://openalex.org/W1991223634","doi":"https://doi.org/10.1142/s0219427901000291","title":"Determination of Context Window Size","display_name":"Determination of Context Window Size","publication_year":2001,"publication_date":"2001-03-01","ids":{"openalex":"https://openalex.org/W1991223634","doi":"https://doi.org/10.1142/s0219427901000291","mag":"1991223634"},"language":"en","primary_location":{"id":"doi:10.1142/s0219427901000291","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427901000291","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/A5019765601","display_name":"KEI YUEN HUNG","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":true,"raw_author_name":"KEI YUEN HUNG","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, People's Republic of China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029313981","display_name":"Robert W. P. Luk","orcid":"https://orcid.org/0000-0002-9310-8867"},"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":"ROBERT LUK","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, People's Republic of China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105788983","display_name":"Daniel Yeung","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":"DANIEL YEUNG","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, People's Republic of China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043016512","display_name":"Fu-Lai Chung","orcid":"https://orcid.org/0000-0001-5294-8168"},"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":"KORRIS CHUNG","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, People's Republic of China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109101425","display_name":"WENHUO SHU","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"WENHUO SHU","raw_affiliation_strings":["Department of Computer Science and Engineering, Harbin Institute of Engineering, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Harbin Institute of Engineering, People's Republic of China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019765601"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.13068228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"14","issue":"01","first_page":"71","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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":0.9944999814033508,"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/spurious-relationship","display_name":"Spurious relationship","score":0.738818883895874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6490863561630249},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6455944180488586},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.572516918182373},{"id":"https://openalex.org/keywords/quartile","display_name":"Quartile","score":0.5429373383522034},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.48926541209220886},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.4830054044723511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4496413767337799},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4300580620765686},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4189947545528412},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36783427000045776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.302262544631958},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25308504700660706},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07257285714149475}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.738818883895874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6490863561630249},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6455944180488586},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.572516918182373},{"id":"https://openalex.org/C68443243","wikidata":"https://www.wikidata.org/wiki/Q2786686","display_name":"Quartile","level":3,"score":0.5429373383522034},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.48926541209220886},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.4830054044723511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496413767337799},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4300580620765686},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4189947545528412},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36783427000045776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.302262544631958},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25308504700660706},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07257285714149475},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219427901000291","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427901000291","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:10397/31171","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/31171","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":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"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":13,"referenced_works":["https://openalex.org/W105408792","https://openalex.org/W1505652865","https://openalex.org/W1593045043","https://openalex.org/W1916540122","https://openalex.org/W1940278502","https://openalex.org/W2007709031","https://openalex.org/W2120234416","https://openalex.org/W2153028052","https://openalex.org/W2163329495","https://openalex.org/W2398845498","https://openalex.org/W2614237344","https://openalex.org/W2997757304","https://openalex.org/W4360598533"],"related_works":["https://openalex.org/W2162899405","https://openalex.org/W3113091479","https://openalex.org/W941090075","https://openalex.org/W2044987316","https://openalex.org/W3134374554","https://openalex.org/W2237480245","https://openalex.org/W2519167559","https://openalex.org/W2075065631","https://openalex.org/W4288358396","https://openalex.org/W4311248832"],"abstract_inverted_index":{"Context":[0,50],"windows":[1],"are":[2,113],"important":[3],"for":[4,39,53,127,168,183],"a":[5],"variety":[6],"of":[7,23,36,76,85,99,118,157,189],"natural":[8],"language":[9],"analysis":[10],"and":[11,20,27,102,133,153],"processing.":[12],"A":[13,115],"trade-off":[14],"exists":[15],"between":[16,130,134],"the":[17,21,24,34,37,44,49,60,73,79,83,88,93,100,103,141,154,163,177],"task":[18],"performance":[19],"size":[22,35,52,117],"context.":[25,80],"Lucassen":[26],"Mercer":[28],"used":[29],"mutual":[30,158],"information":[31],"to":[32,47,72,123],"determine":[33,48],"context":[38],"English":[40],"text.":[41,55],"We":[42,160],"apply":[43],"same":[45],"technique":[46],"window":[51,116],"Chinese":[54],"In":[56],"addition,":[57],"we":[58],"use":[59],"association":[61,67,89,104,151,178],"score,":[62],"proposed":[63],"by":[64],"Church.":[65],"The":[66],"score":[68,90,105,179],"is":[69,96,146,165,180],"directly":[70],"related":[71],"prediction":[74],"ability":[75],"units":[77],"in":[78],"To":[81],"reduce":[82],"effects":[84],"spurious":[86,150],"associations,":[87],"values":[91],"at":[92],"N%":[94],"quartile":[95],"used,":[97],"instead":[98],"maximum,":[101],"derived":[106],"from":[107],"low":[108],"frequency":[109],"occurrences":[110],"(i.e.":[111],"&lt;5)":[112],"discarded.":[114],"9":[119],"characters":[120,131],"was":[121],"found":[122],"be":[124],"large":[125],"enough":[126],"most":[128],"associations":[129],"themselves,":[132],"words":[135],"themselves.":[136],"An":[137],"alternative":[138],"approach":[139],"using":[140],"(nonparametric)":[142],"lambda":[143],"statistic":[144,164],"LB":[145],"examined,":[147],"which":[148],"overcomes":[149],"problems":[152],"averaging":[155],"effect":[156],"information.":[159],"conclude":[161],"that":[162],"more":[166,181],"suitable":[167,182],"exhaustive":[169],"contextual":[170,185],"models":[171,186],"(e.g.":[172,187],"variable":[173],"N-gram":[174],"models)":[175],"whereas":[176],"non-exhaustive":[184],"identification":[188],"collocation).":[190]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
