{"id":"https://openalex.org/W1977073624","doi":"https://doi.org/10.1145/2600428.2609597","title":"Continuous word embeddings for detecting local text reuses at the semantic level","display_name":"Continuous word embeddings for detecting local text reuses at the semantic level","publication_year":2014,"publication_date":"2014-07-03","ids":{"openalex":"https://openalex.org/W1977073624","doi":"https://doi.org/10.1145/2600428.2609597","mag":"1977073624"},"language":"en","primary_location":{"id":"doi:10.1145/2600428.2609597","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2600428.2609597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval","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/A5100360407","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0003-0947-4942"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026984917","display_name":"Jihua Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Kang","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101550087","display_name":"Jin Qian","orcid":"https://orcid.org/0000-0001-5617-696X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Qian","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088834359","display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":2.1576,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.92533468,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"797","last_page":"806"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T11478","display_name":"Caching and Content Delivery","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.98580002784729,"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":0.8446930646896362},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6685420274734497},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.577004075050354},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5357171297073364},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47594642639160156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43946823477745056},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41406819224357605},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4133703112602234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8446930646896362},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6685420274734497},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.577004075050354},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5357171297073364},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47594642639160156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43946823477745056},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41406819224357605},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4133703112602234},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2600428.2609597","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2600428.2609597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1573082642","https://openalex.org/W1614298861","https://openalex.org/W1835419070","https://openalex.org/W1966385142","https://openalex.org/W1968197683","https://openalex.org/W1977729554","https://openalex.org/W1984309565","https://openalex.org/W2000625227","https://openalex.org/W2012833704","https://openalex.org/W2031637148","https://openalex.org/W2044434631","https://openalex.org/W2049229305","https://openalex.org/W2067432306","https://openalex.org/W2100495367","https://openalex.org/W2103305545","https://openalex.org/W2109025268","https://openalex.org/W2109803107","https://openalex.org/W2113459411","https://openalex.org/W2124158580","https://openalex.org/W2132069633","https://openalex.org/W2138806976","https://openalex.org/W2148578434","https://openalex.org/W2148885851","https://openalex.org/W2153180170","https://openalex.org/W2153579005","https://openalex.org/W2158139315","https://openalex.org/W2158899491","https://openalex.org/W2160149277","https://openalex.org/W2164019165","https://openalex.org/W2166023018","https://openalex.org/W2166473218","https://openalex.org/W2166490638","https://openalex.org/W2167302605","https://openalex.org/W2221852422","https://openalex.org/W2250434988","https://openalex.org/W2251797717","https://openalex.org/W2289346390","https://openalex.org/W2293597654","https://openalex.org/W2604272474","https://openalex.org/W2913932916","https://openalex.org/W2998704965","https://openalex.org/W4285719527","https://openalex.org/W6680532216"],"related_works":["https://openalex.org/W2485872624","https://openalex.org/W2159024673","https://openalex.org/W3001987467","https://openalex.org/W2968165261","https://openalex.org/W1603161560","https://openalex.org/W4252190074","https://openalex.org/W2154676777","https://openalex.org/W2296205523","https://openalex.org/W4206165639","https://openalex.org/W2050712820"],"abstract_inverted_index":{"Text":[0],"reuse":[1],"is":[2,189],"a":[3,7,72],"common":[4],"phenomenon":[5],"in":[6,52,63,154],"variety":[8],"of":[9,17,21,34,95,112,114,170,185,196],"user-generated":[10],"content.":[11],"Along":[12],"with":[13],"the":[14,81,99,144,168,171,183,186],"quick":[15],"expansion":[16],"social":[18],"media,":[19],"reuses":[20,38,79],"local":[22,37,78],"text":[23,105,130],"are":[24,124,174],"occurring":[25],"much":[26],"more":[27],"frequently":[28],"than":[29,151,179,194],"ever":[30],"before.":[31],"The":[32],"task":[33],"detecting":[35],"these":[36],"serves":[39],"as":[40],"an":[41],"essential":[42],"step":[43],"for":[44,84],"many":[45],"applications.":[46],"It":[47],"has":[48],"attracted":[49],"extensive":[50],"attention":[51],"recent":[53],"years.":[54],"However,":[55],"semantic":[56,82,100],"level":[57,83,101],"similarities":[58,102],"have":[59],"not":[60],"received":[61],"consideration":[62],"most":[64],"previous":[65,180],"works.":[66],"In":[67,107],"this":[68],"paper,":[69],"we":[70],"introduce":[71],"novel":[73],"method":[74,173,188],"to":[75,90,97,109,126,136,160,191],"efficiently":[76],"detect":[77],"at":[80],"large":[85],"scale":[86],"problems.":[87],"We":[88],"propose":[89],"use":[91],"continuous":[92],"vector":[93],"representations":[94],"words":[96],"capture":[98],"between":[103],"short":[104],"segments.":[106],"order":[108],"handle":[110],"tens":[111],"billions":[113],"documents,":[115],"methods":[116,123,146],"based":[117],"on":[118],"information":[119],"geometry":[120],"and":[121,128],"hashing":[122,199],"introduced":[125],"aggregate":[127],"map":[129],"segments":[131],"presented":[132],"by":[133],"word":[134],"embeddings":[135],"binary":[137],"hash":[138],"codes.":[139],"Experimental":[140],"results":[141],"demonstrate":[142],"that":[143,195],"proposed":[145,172,187],"achieve":[147],"significantly":[148],"better":[149,193],"performance":[150],"state-of-the-art":[152],"approaches":[153],"all":[155],"six":[156],"document":[157],"collections":[158],"belonging":[159],"four":[161],"different":[162],"categories.":[163],"At":[164],"some":[165,197],"recall":[166],"levels,":[167],"precisions":[169],"even":[175],"10":[176],"times":[177],"higher":[178],"methods.":[181,200],"Moreover,":[182],"efficiency":[184],"comparable":[190],"or":[192],"other":[198]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}