{"id":"https://openalex.org/W2743135392","doi":"https://doi.org/10.1109/icnsc.2017.8000087","title":"Aggregating sentence-level features for Chinese near-duplicate document detection","display_name":"Aggregating sentence-level features for Chinese near-duplicate document detection","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2743135392","doi":"https://doi.org/10.1109/icnsc.2017.8000087","mag":"2743135392"},"language":"en","primary_location":{"id":"doi:10.1109/icnsc.2017.8000087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc.2017.8000087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 14th International Conference on Networking, Sensing and Control (ICNSC)","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":"https://openalex.org/A5112723522","display_name":"Yan Liang","orcid":"https://orcid.org/0000-0002-9621-0330"},"institutions":[{"id":"https://openalex.org/I2801345734","display_name":"China Academy of Engineering Physics","ror":"https://ror.org/039vqpp67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2801345734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Liang","raw_affiliation_strings":["Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China","institution_ids":["https://openalex.org/I2801345734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064492985","display_name":"Yizheng Tao","orcid":"https://orcid.org/0000-0003-4672-2570"},"institutions":[{"id":"https://openalex.org/I2801345734","display_name":"China Academy of Engineering Physics","ror":"https://ror.org/039vqpp67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2801345734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizheng Tao","raw_affiliation_strings":["Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China","institution_ids":["https://openalex.org/I2801345734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021773319","display_name":"Ning Feng","orcid":"https://orcid.org/0000-0001-8452-0959"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Feng","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113818733","display_name":"Zhenjing Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I2801345734","display_name":"China Academy of Engineering Physics","ror":"https://ror.org/039vqpp67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2801345734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjing Wan","raw_affiliation_strings":["Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China","institution_ids":["https://openalex.org/I2801345734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100771997","display_name":"Xu Feng","orcid":"https://orcid.org/0000-0002-8226-9403"},"institutions":[{"id":"https://openalex.org/I2801345734","display_name":"China Academy of Engineering Physics","ror":"https://ror.org/039vqpp67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2801345734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Xu","raw_affiliation_strings":["Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China","institution_ids":["https://openalex.org/I2801345734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072570597","display_name":"Xue Jiang","orcid":"https://orcid.org/0000-0003-2109-8660"},"institutions":[{"id":"https://openalex.org/I2801345734","display_name":"China Academy of Engineering Physics","ror":"https://ror.org/039vqpp67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2801345734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Jiang","raw_affiliation_strings":["Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China","institution_ids":["https://openalex.org/I2801345734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082429541","display_name":"Shan Gao","orcid":"https://orcid.org/0009-0006-2695-2968"},"institutions":[{"id":"https://openalex.org/I2801345734","display_name":"China Academy of Engineering Physics","ror":"https://ror.org/039vqpp67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2801345734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Gao","raw_affiliation_strings":["Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Apllication, China Academy of Engineering Physics, Mianyang, China","institution_ids":["https://openalex.org/I2801345734"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"174","last_page":"179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9939000010490417,"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":0.9916999936103821,"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":0.8036726713180542},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7955560684204102},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6064494848251343},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5787113904953003},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.531525194644928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5257319211959839},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5181571245193481},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4981212615966797},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4819624125957489},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45360904932022095},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3746635615825653},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35744422674179077},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33469730615615845},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09149563312530518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036726713180542},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7955560684204102},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6064494848251343},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5787113904953003},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.531525194644928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5257319211959839},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5181571245193481},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4981212615966797},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4819624125957489},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45360904932022095},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3746635615825653},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35744422674179077},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33469730615615845},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09149563312530518},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icnsc.2017.8000087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc.2017.8000087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 14th International Conference on Networking, Sensing and Control (ICNSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W361458199","https://openalex.org/W1625138908","https://openalex.org/W1877838289","https://openalex.org/W1984309565","https://openalex.org/W1989383714","https://openalex.org/W2004025009","https://openalex.org/W2021952182","https://openalex.org/W2062152380","https://openalex.org/W2067432306","https://openalex.org/W2096929438","https://openalex.org/W2109803107","https://openalex.org/W2119057313","https://openalex.org/W2120058970","https://openalex.org/W2132072504","https://openalex.org/W2145349611","https://openalex.org/W2148885851","https://openalex.org/W2152565070","https://openalex.org/W2152832716","https://openalex.org/W2153180170","https://openalex.org/W4230940751"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Detecting":[0],"near-duplicate":[1,32,91],"documents":[2],"efficiently":[3],"is":[4,135],"an":[5],"indispensable":[6],"capability":[7],"for":[8,31],"many":[9],"applications,":[10],"such":[11],"as":[12],"searching":[13],"engines,":[14],"information":[15,76,108],"retrieval":[16],"systems,":[17],"and":[18,54,64,68,88,105,145,154],"recommendation":[19],"systems.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24,72,94,117],"propose":[25],"a":[26,36,114,152],"novel":[27],"content":[28],"presentation":[29],"method":[30,163],"document":[33,92,171],"detection":[34],"from":[35],"large":[37],"collection":[38],"of":[39,50,77,90,99,109,127,141],"Chinese":[40,170],"documents.":[41],"The":[42],"proposed":[43,161],"method,":[44],"called":[45],"multi-aggregation":[46],"fingerprint":[47],"(MAF),":[48],"consists":[49],"sentence-level":[51],"feature":[52,121,134,143],"extraction":[53],"multi-feature":[55],"aggregation.":[56],"Compared":[57],"with":[58],"terms,":[59],"sentences":[60,78],"are":[61,149],"more":[62,66],"representative":[63],"contain":[65],"abundant":[67],"integrated":[69],"information.":[70],"Thus,":[71],"extract":[73],"the":[74,81,86,103,106,119,125,130,138,142,160,169],"crucial":[75],"to":[79,113,137],"form":[80],"sentence":[82,100,110,120,133,147],"features.":[83],"To":[84],"improve":[85],"accuracy":[87],"efficiency":[89],"detection,":[93],"exploit":[95],"both":[96],"holistic":[97],"characteristics":[98],"features":[101,111,128,148],"in":[102,129],"dataset":[104],"statistic":[107],"belonging":[112],"document.":[115],"Accordingly,":[116],"split":[118],"space":[122],"based":[123],"on":[124,168],"distribution":[126],"dataset.":[131,172],"Each":[132],"assigned":[136],"nearest":[139],"partition":[140],"space,":[144],"multiple":[146],"aggregated":[150],"into":[151],"compact":[153],"global":[155],"fingerprint.":[156],"Experimental":[157],"results":[158,167],"show":[159],"MAF":[162],"can":[164],"produce":[165],"competitive":[166]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}