{"id":"https://openalex.org/W4318477599","doi":"https://doi.org/10.1145/3570725","title":"An Efficient and Robust Semantic Hashing Framework for Similar Text Search","display_name":"An Efficient and Robust Semantic Hashing Framework for Similar Text Search","publication_year":2023,"publication_date":"2023-01-30","ids":{"openalex":"https://openalex.org/W4318477599","doi":"https://doi.org/10.1145/3570725"},"language":"en","primary_location":{"id":"doi:10.1145/3570725","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570725","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","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/A5077791803","display_name":"Liyang He","orcid":"https://orcid.org/0000-0002-1609-0747"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liyang He","raw_affiliation_strings":["University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085496384","display_name":"Zhenya Huang","orcid":"https://orcid.org/0000-0003-1661-0420"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenya Huang","raw_affiliation_strings":["University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048237545","display_name":"Enhong Chen","orcid":"https://orcid.org/0000-0002-4835-4102"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhong Chen","raw_affiliation_strings":["University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453156","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-6956-5550"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000135168","display_name":"Shiwei Tong","orcid":"https://orcid.org/0000-0002-4218-0236"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwei Tong","raw_affiliation_strings":["University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446057","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0001-8853-0126"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085254654","display_name":"Defu Lian","orcid":"https://orcid.org/0000-0002-3507-9607"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Defu Lian","raw_affiliation_strings":["Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China, China and State Key Laboratory of Cognitive Intelligence, China"],"affiliations":[{"raw_affiliation_string":"Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China, China and State Key Laboratory of Cognitive Intelligence, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069365665","display_name":"Shijin Wang","orcid":"https://orcid.org/0000-0002-4788-0530"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shijin Wang","raw_affiliation_strings":["iFLYTEK AI Research (Central China) iFLYTEK Co., Ltd, China and State Key Laboratory of Cognitive Intelligence, China"],"affiliations":[{"raw_affiliation_string":"iFLYTEK AI Research (Central China) iFLYTEK Co., Ltd, China and State Key Laboratory of Cognitive Intelligence, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5077791803"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.9794,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76734433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9947999715805054,"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":0.9886000156402588,"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":0.8189958333969116},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6725159287452698},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6263701319694519},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.47099488973617554},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.39436131715774536},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38990581035614014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32342851161956787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189958333969116},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6725159287452698},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6263701319694519},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.47099488973617554},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.39436131715774536},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38990581035614014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32342851161956787},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3570725","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570725","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1483313504","https://openalex.org/W1603598191","https://openalex.org/W1835419070","https://openalex.org/W1974647172","https://openalex.org/W1978475816","https://openalex.org/W1982193706","https://openalex.org/W1999529867","https://openalex.org/W2004329216","https://openalex.org/W2053966956","https://openalex.org/W2062296170","https://openalex.org/W2077948748","https://openalex.org/W2090398718","https://openalex.org/W2122196799","https://openalex.org/W2124509324","https://openalex.org/W2126210882","https://openalex.org/W2136189984","https://openalex.org/W2147152072","https://openalex.org/W2147717514","https://openalex.org/W2152437528","https://openalex.org/W2155622664","https://openalex.org/W2162006472","https://openalex.org/W2279511887","https://openalex.org/W2513500384","https://openalex.org/W2533021784","https://openalex.org/W2539671052","https://openalex.org/W2716747561","https://openalex.org/W2740797857","https://openalex.org/W2744136723","https://openalex.org/W2798666412","https://openalex.org/W2806681694","https://openalex.org/W2884517879","https://openalex.org/W2892181857","https://openalex.org/W2913932916","https://openalex.org/W2946436477","https://openalex.org/W2954778009","https://openalex.org/W2955931418","https://openalex.org/W2962919781","https://openalex.org/W2963213486","https://openalex.org/W2963605131","https://openalex.org/W2964369530","https://openalex.org/W2979413472","https://openalex.org/W2985730480","https://openalex.org/W3004047605","https://openalex.org/W3012800455","https://openalex.org/W3015310959","https://openalex.org/W3033276647","https://openalex.org/W3034368386","https://openalex.org/W3034612156","https://openalex.org/W3035623165","https://openalex.org/W3035640753","https://openalex.org/W3036320503","https://openalex.org/W3045279034","https://openalex.org/W3080281801","https://openalex.org/W3094844246","https://openalex.org/W3095721108","https://openalex.org/W3098468692","https://openalex.org/W3102111601","https://openalex.org/W3102844761","https://openalex.org/W3136528130","https://openalex.org/W3138154797","https://openalex.org/W3156298872","https://openalex.org/W3157577978","https://openalex.org/W3166125679","https://openalex.org/W3166944102","https://openalex.org/W3172429379","https://openalex.org/W3173285067","https://openalex.org/W3198098536","https://openalex.org/W3200545253","https://openalex.org/W3217620713","https://openalex.org/W4214607697","https://openalex.org/W4285208448"],"related_works":["https://openalex.org/W2069568684","https://openalex.org/W3019245231","https://openalex.org/W1984081611","https://openalex.org/W2376661060","https://openalex.org/W2119251656","https://openalex.org/W2948607823","https://openalex.org/W2171626009","https://openalex.org/W4387251676","https://openalex.org/W1835589799","https://openalex.org/W4385261619"],"abstract_inverted_index":{"Similar":[0],"text":[1,43,218,293,321],"search":[2,26,38,44,97,279],"aims":[3],"to":[4,8,69,109,136,157,208,243,267,282],"find":[5,70],"texts":[6,33,89],"relevant":[7,75],"a":[9,13,41,71,153,162,194,222,235,309],"given":[10],"query":[11],"from":[12,152,322],"database,":[14],"which":[15,86,176,276],"is":[16,68,105],"fundamental":[17],"in":[18,61,149,173,182,188,263,338,355],"many":[19],"information":[20,138,227],"retrieval":[21,122],"applications,":[22,175],"such":[23],"as":[24,58,228,230,362,364],"question":[25],"and":[27,50,78,212,349,353,358],"exercise":[28],"search.":[29,219],"Since":[30],"millions":[31],"of":[32,48,74,165,171,180,224,272,288,330,351,369],"always":[34,143],"exist":[35],"behind":[36],"practical":[37],"engine":[39],"systems,":[40],"well-developed":[42],"system":[45],"usually":[46],"consists":[47],"recall":[49,55],"ranking":[51],"stages.":[52],"Specifically,":[53,220],"the":[54,59,62,65,110,125,145,150,178,210,232,245,257,264,269,273,284,289,316,323,328,347,365],"stage":[56],"serves":[57],"basis":[60],"system,":[63],"where":[64,256],"main":[66],"purpose":[67],"small":[72],"set":[73],"candidates":[76],"accurately":[77],"efficiently.":[79],"Towards":[80],"this":[81,186,189],"goal,":[82],"deep":[83],"semantic":[84,198,226,324],"hashing,":[85],"projects":[87],"original":[88],"into":[90],"compact":[91,114,129,213,246,359],"hash":[92,103,115,130,183,214,247,331,360],"codes,":[93,361],"can":[94,120,260,277],"support":[95],"good":[96],"performance.":[98],"However,":[99],"learning":[100,128,259,274],"desired":[101],"textual":[102,166],"codes":[104,116,131,148,215],"extremely":[106],"difficult":[107],"due":[108,135],"following":[111],"problems.":[112],"First,":[113],"(with":[117],"short":[118],"length)":[119],"improve":[121],"efficiency,":[123],"but":[124],"demand":[126],"for":[127,204,216,301,319],"cannot":[132],"guarantee":[133],"accuracy":[134],"severe":[137],"loss.":[139],"Second,":[140],"existing":[141],"methods":[142],"learn":[144,209],"unevenly":[146],"distributed":[147],"space":[151,266],"local":[154],"perspective,":[155],"leading":[156],"unsatisfactory":[158],"code-balance":[159],"results.":[160],"Third,":[161],"large":[163],"fraction":[164],"data":[167],"contains":[168],"various":[169],"types":[170],"noise":[172,317],"real-world":[174,340],"causes":[177],"deviation":[179,325],"semantics":[181],"codes.":[184,332],"To":[185],"end,":[187],"paper,":[190],"we":[191,251,295,334],"first":[192],"propose":[193,296],"general":[195],"unsupervised":[196],"encoder-decoder":[197,311],"hashing":[199,258],"framework,":[200],"namely":[201],"MASH":[202,352],"(short":[203,300],"Memory-bAsed":[205,303],"Semantic":[206,304],"Hashing),":[207],"balanced":[211,357],"similar":[217],"with":[221],"target":[223],"retaining":[225],"much":[229],"possible,":[231],"encoder":[233],"introduces":[234],"novel":[236],"relevance":[237],"constraint":[238],"among":[239],"informative":[240],"high-dimensional":[241],"representations":[242],"guide":[244],"code":[248,270],"learning.":[249],"Then,":[250],"design":[252],"an":[253,297],"external":[254],"memory":[255],"be":[261],"optimized":[262],"global":[265],"ensure":[268],"balance":[271],"results,":[275],"promote":[278],"efficiency.":[280],"Besides,":[281],"alleviate":[283],"performance":[285],"degradation":[286],"problem":[287],"model":[290,306],"caused":[291],"by":[292,307],"noise,":[294],"improved":[298],"SMASH":[299,354],"denoiSing":[302],"Hashing)":[305],"incorporating":[308],"noise-aware":[310],"framework.":[312],"This":[313],"framework":[314],"considers":[315],"degree":[318],"each":[320],"aspect,":[326],"ensuring":[327],"robustness":[329],"Finally,":[333],"conduct":[335],"extensive":[336],"experiments":[337],"three":[339],"datasets.":[341],"The":[342],"experimental":[343],"results":[344],"clearly":[345],"demonstrate":[346],"effectiveness":[348],"efficiency":[350],"generating":[356],"well":[363],"superior":[366],"denoising":[367],"ability":[368],"SMASH.":[370]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}