{"id":"https://openalex.org/W2022647735","doi":"https://doi.org/10.1145/2830544.2830548","title":"A Framework for Collocation Error Correction in Web Pages and Text Documents","display_name":"A Framework for Collocation Error Correction in Web Pages and Text Documents","publication_year":2015,"publication_date":"2015-09-29","ids":{"openalex":"https://openalex.org/W2022647735","doi":"https://doi.org/10.1145/2830544.2830548","mag":"2022647735"},"language":"en","primary_location":{"id":"doi:10.1145/2830544.2830548","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830544.2830548","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","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/A5034559228","display_name":"Alan Varghese","orcid":null},"institutions":[{"id":"https://openalex.org/I166088655","display_name":"Montclair State University","ror":"https://ror.org/01nxc2t48","country_code":"US","type":"education","lineage":["https://openalex.org/I166088655"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Varghese","raw_affiliation_strings":["Montclair State University, Montclair, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montclair State University, Montclair, NJ, USA","institution_ids":["https://openalex.org/I166088655"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090253347","display_name":"Aparna S. Varde","orcid":"https://orcid.org/0000-0002-3170-2510"},"institutions":[{"id":"https://openalex.org/I166088655","display_name":"Montclair State University","ror":"https://ror.org/01nxc2t48","country_code":"US","type":"education","lineage":["https://openalex.org/I166088655"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aparna S. Varde","raw_affiliation_strings":["Montclair State University, Montclair, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montclair State University, Montclair, NJ, USA","institution_ids":["https://openalex.org/I166088655"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101892033","display_name":"Jing Peng","orcid":"https://orcid.org/0000-0001-8822-310X"},"institutions":[{"id":"https://openalex.org/I166088655","display_name":"Montclair State University","ror":"https://ror.org/01nxc2t48","country_code":"US","type":"education","lineage":["https://openalex.org/I166088655"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Peng","raw_affiliation_strings":["Montclair State University, Montclair, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montclair State University, Montclair, NJ, USA","institution_ids":["https://openalex.org/I166088655"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015721352","display_name":"Eileen Fitzpatrick","orcid":null},"institutions":[{"id":"https://openalex.org/I166088655","display_name":"Montclair State University","ror":"https://ror.org/01nxc2t48","country_code":"US","type":"education","lineage":["https://openalex.org/I166088655"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eileen Fitzpatrick","raw_affiliation_strings":["Montclair State University, Montclair, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montclair State University, Montclair, NJ, USA","institution_ids":["https://openalex.org/I166088655"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166088655"],"apc_list":null,"apc_paid":null,"fwci":0.8731,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82412406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"17","issue":"1","first_page":"14","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T13629","display_name":"Text Readability and Simplification","score":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.8878786563873291},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.585643470287323},{"id":"https://openalex.org/keywords/collocation","display_name":"Collocation (remote sensing)","score":0.5564184188842773},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5397442579269409},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46472981572151184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4516623616218567},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42619356513023376},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3972330689430237},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25112345814704895},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18351632356643677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8878786563873291},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.585643470287323},{"id":"https://openalex.org/C80023036","wikidata":"https://www.wikidata.org/wiki/Q5147531","display_name":"Collocation (remote sensing)","level":2,"score":0.5564184188842773},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5397442579269409},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46472981572151184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4516623616218567},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42619356513023376},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3972330689430237},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25112345814704895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18351632356643677},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2830544.2830548","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830544.2830548","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W32429889","https://openalex.org/W1014327228","https://openalex.org/W1508977358","https://openalex.org/W1599833183","https://openalex.org/W1670263352","https://openalex.org/W1966954239","https://openalex.org/W1985339368","https://openalex.org/W2031707636","https://openalex.org/W2053523303","https://openalex.org/W2088397896","https://openalex.org/W2093641143","https://openalex.org/W2097606805","https://openalex.org/W2099083511","https://openalex.org/W2102381086","https://openalex.org/W2114544510","https://openalex.org/W2137115322","https://openalex.org/W2170066533","https://openalex.org/W2951082877","https://openalex.org/W6831690384"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W4241418540","https://openalex.org/W1508895727","https://openalex.org/W2725786787","https://openalex.org/W4283160672","https://openalex.org/W1875930651"],"abstract_inverted_index":{"Much":[0],"of":[1,44,87,138],"the":[2,45,64,112,136,142],"English":[3,48],"in":[4,25,35,77,135,150,160,175,180],"text":[5,88],"documents":[6,89,183],"today":[7],"comes":[8],"from":[9,63],"nonnative":[10],"speakers.":[11,21],"Web":[12,83,163],"searches":[13],"are":[14],"also":[15,173],"conducted":[16],"very":[17],"often":[18],"by":[19],"non-native":[20],"Though":[22],"highly":[23],"qualified":[24],"their":[26],"respective":[27,65],"fields,":[28],"these":[29],"speakers":[30],"could":[31,74],"potentially":[32],"make":[33],"errors":[34,73,103],"collocation,":[36],"e.g.,":[37,165],"\"dark":[38],"money\"":[39,51],"and":[40,52,90,104,147,184],"\"stock":[41,53],"agora\"":[42],"(instead":[43],"more":[46],"appropriate":[47],"expressions":[49],"\"black":[50],"market\"":[54],"respectively).":[55],"These":[56],"may":[57],"arise":[58],"due":[59],"to":[60,99,128,131,187],"literal":[61],"translation":[62],"speaker's":[66],"native":[67],"language":[68,122],"or":[69],"other":[70],"factors.":[71],"Such":[72],"cause":[75],"problems":[76],"contexts":[78],"such":[79,101],"as":[80],"querying":[81,164],"over":[82],"pages,":[84],"correct":[85],"understanding":[86],"more.":[91],"This":[92,114],"paper":[93],"proposes":[94],"a":[95],"framework":[96,115,144],"called":[97],"CollOrder":[98],"detect":[100],"collocation":[102,132],"suggest":[105],"correctly":[106],"ordered":[107],"collocated":[108],"responses":[109,130],"for":[110],"improving":[111],"semantics.":[113],"integrates":[116],"machine":[117,181],"learning":[118],"approaches":[119],"with":[120,145],"natural":[121],"processing":[123],"techniques,":[124],"proposing":[125],"suitable":[126],"heuristics":[127],"provide":[129],"errors,":[133],"ranked":[134],"order":[137],"correctness.":[139],"We":[140,153],"discuss":[141],"proposed":[143],"algorithms":[146],"experimental":[148],"evaluation":[149],"this":[151],"paper.":[152],"claim":[154],"that":[155],"it":[156],"would":[157,172],"be":[158],"useful":[159],"semantically":[161],"enhancing":[162],"financial":[166],"news,":[167],"online":[168],"shopping":[169],"etc.":[170],"It":[171],"help":[174],"providing":[176],"automated":[177],"error":[178],"correction":[179],"translated":[182],"offering":[185],"assistance":[186],"people":[188],"using":[189],"ESL":[190],"tools.":[191]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}