{"id":"https://openalex.org/W2605220275","doi":"https://doi.org/10.3233/978-1-61499-484-8-2063","title":"A Novel Parallel Deduplication and Noise Reduction Method for Vertical Search Engine","display_name":"A Novel Parallel Deduplication and Noise Reduction Method for Vertical Search Engine","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2605220275","doi":"https://doi.org/10.3233/978-1-61499-484-8-2063","mag":"2605220275"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-484-8-2063","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-484-8-2063","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","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/A5116359701","display_name":"Song Junjie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642607","display_name":"Jin Liu","orcid":"https://orcid.org/0000-0001-7249-698X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029730758","display_name":"Ming Ni","orcid":"https://orcid.org/0000-0002-3910-0127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ni Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740275","display_name":"Li Fei","orcid":"https://orcid.org/0000-0003-1308-4787"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100599734","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-2778-4381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38963964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2063","last_page":"2069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9039000272750854,"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":0.9039000272750854,"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/data-deduplication","display_name":"Data deduplication","score":0.8889530897140503},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6621970534324646},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6134287714958191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5317710041999817},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5097014904022217},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22572031617164612},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17613154649734497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16568049788475037},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.040312618017196655}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8889530897140503},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6621970534324646},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6134287714958191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5317710041999817},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5097014904022217},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22572031617164612},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17613154649734497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16568049788475037},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.040312618017196655},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-61499-484-8-2063","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-484-8-2063","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"mag:2605220275","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/intcompsymp/ics2014.html#SongLNLW14","pdf_url":null,"source":{"id":"https://openalex.org/S4306419857","display_name":"International Conference on Supercomputing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"International Conference on Supercomputing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W3034789145","https://openalex.org/W4367628250","https://openalex.org/W4388819787"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,22],"method":[4,14,23,82],"noise":[5,50,85],"reduction":[6,86],"of":[7,24,43,83],"topic":[8],"specific":[9],"web":[10,27,72,84,90,102],"pages.":[11,73,91],"The":[12,92],"novel":[13],"is":[15],"based":[16],"on":[17],"the":[18,37,55,62,70,81,97],"frequency":[19,38],"statistics":[20],"and":[21,32,51,57,66,87,105],"deleting":[25,88],"duplicate":[26,71,89,101],"pages":[28,103],"through":[29],"hash":[30,63],"table":[31],"inverted":[33],"index.":[34],"According":[35],"to":[36,48,68,79],"statistics,":[39],"those":[40],"frequent":[41],"occurrences":[42],"clauses":[44,56],"will":[45,60],"be":[46,49,52],"considered":[47],"deleted.":[53],"Then":[54],"their":[58],"urls":[59],"become":[61],"table's":[64],"keys":[65],"values":[67],"search":[69],"We":[74],"use":[75],"four":[76],"Map-Reduce":[77],"tasks":[78],"ensure":[80],"experiment":[93],"result":[94],"shows":[95],"that":[96],"algorithm":[98],"can":[99],"remove":[100],"efficiently":[104],"accurately.":[106]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
