{"id":"https://openalex.org/W2099750989","doi":"https://doi.org/10.1109/nlpke.2008.4906751","title":"Semantic keywords-based duplicated web pages removing","display_name":"Semantic keywords-based duplicated web pages removing","publication_year":2008,"publication_date":"2008-10-01","ids":{"openalex":"https://openalex.org/W2099750989","doi":"https://doi.org/10.1109/nlpke.2008.4906751","mag":"2099750989"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2008.4906751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2008.4906751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 International Conference on Natural Language Processing and Knowledge Engineering","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Yunhe Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"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":"Yunhe Weng","raw_affiliation_strings":["School of Information Engineering, Beijing University of Posts and Telecommunications, China","Sch. of Inf., Beijing Univ. of Posts & Tele-Commun., Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Sch. of Inf., Beijing Univ. of Posts & Tele-Commun., Beijing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440277","display_name":"Lei Li","orcid":"https://orcid.org/0000-0002-0688-9619"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"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":"Lei Li","raw_affiliation_strings":["School of Information Engineering, Beijing University of Posts and Telecommunications, China","Sch. of Inf., Beijing Univ. of Posts & Tele-Commun., Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Sch. of Inf., Beijing Univ. of Posts & Tele-Commun., Beijing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101037440","display_name":"Yixin Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"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":"Yixin Zhong","raw_affiliation_strings":["School of Information Engineering, Beijing University of Posts and Telecommunications, China","Sch. of Inf., Beijing Univ. of Posts & Tele-Commun., Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Sch. of Inf., Beijing Univ. of Posts & Tele-Commun., Beijing","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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/T11719","display_name":"Data Quality and Management","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9805999994277954,"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":0.8594220876693726},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6478776335716248},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6323009729385376},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6093581914901733},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.6056726574897766},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5545467734336853},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5347352027893066},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.5257899761199951},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5123423337936401},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.49791407585144043},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.4802142083644867},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.41152769327163696},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.16229131817817688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14468073844909668},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0704178512096405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8594220876693726},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6478776335716248},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6323009729385376},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6093581914901733},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.6056726574897766},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5545467734336853},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5347352027893066},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.5257899761199951},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5123423337936401},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.49791407585144043},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.4802142083644867},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.41152769327163696},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.16229131817817688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14468073844909668},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0704178512096405},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nlpke.2008.4906751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2008.4906751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 International Conference on Natural Language Processing and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1609518033","https://openalex.org/W1997657677","https://openalex.org/W2000921048","https://openalex.org/W2007842132","https://openalex.org/W2031313472","https://openalex.org/W2141359307","https://openalex.org/W2349251115","https://openalex.org/W2369315739","https://openalex.org/W4285719527","https://openalex.org/W6636190696","https://openalex.org/W7052533403"],"related_works":["https://openalex.org/W2366430559","https://openalex.org/W2349698472","https://openalex.org/W1585941060","https://openalex.org/W2355823470","https://openalex.org/W2171552258","https://openalex.org/W1985801232","https://openalex.org/W1710908466","https://openalex.org/W2005492920","https://openalex.org/W1975429881","https://openalex.org/W1560244990"],"abstract_inverted_index":{"Because":[0],"of":[1],"many":[2,39],"duplicated":[3,52],"web":[4],"pages":[5,55],"existing":[6],"on":[7,65],"the":[8,35,79,84],"web,":[9],"search":[10,57],"engines":[11],"need":[12],"to":[13,48],"find":[14,49],"and":[15,24,50,72],"remove":[16,51],"them,":[17],"not":[18],"only":[19],"for":[20,29,56],"saving":[21],"process":[22],"time":[23],"hardware":[25],"resource,":[26],"but":[27],"also":[28],"ensuring":[30],"that":[31,82],"users":[32],"can":[33],"get":[34],"result":[36],"information":[37],"without":[38],"replicas.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,60],"propose":[45],"a":[46,62,89],"method":[47],"Chinese":[53],"Web":[54],"engine.":[58],"First":[59],"describe":[61],"scheme":[63],"based":[64],"semantic":[66],"keywords":[67],"combined":[68],"with":[69,78],"sentence":[70],"overlapping,":[71],"then":[73],"show":[74],"an":[75],"implemented":[76],"prototype,":[77],"experimental":[80],"results":[81],"suggest":[83],"prototype":[85],"work":[86],"well":[87],"under":[88],"proper":[90],"setting.":[91]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}