{"id":"https://openalex.org/W2798666412","doi":"https://doi.org/10.1145/3209978.3210090","title":"Deep Semantic Text Hashing with Weak Supervision","display_name":"Deep Semantic Text Hashing with Weak Supervision","publication_year":2018,"publication_date":"2018-06-27","ids":{"openalex":"https://openalex.org/W2798666412","doi":"https://doi.org/10.1145/3209978.3210090","mag":"2798666412"},"language":"en","primary_location":{"id":"doi:10.1145/3209978.3210090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209978.3210090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","raw_type":"proceedings-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/A5003172820","display_name":"Suthee Chaidaroon","orcid":"https://orcid.org/0000-0002-3655-5708"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Suthee Chaidaroon","raw_affiliation_strings":["Santa Clara University, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Santa Clara University, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060141606","display_name":"Travis Ebesu","orcid":null},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Travis Ebesu","raw_affiliation_strings":["Santa Clara University, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Santa Clara University, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101972978","display_name":"Yi Fang","orcid":"https://orcid.org/0000-0001-6572-4315"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Fang","raw_affiliation_strings":["Santa Clara University, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Santa Clara University, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003172820"],"corresponding_institution_ids":["https://openalex.org/I16269868"],"apc_list":null,"apc_paid":null,"fwci":2.0892,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.90689265,"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":"1109","last_page":"1112"},"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":0.9955999851226807,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9915000200271606,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8134889602661133},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6932468414306641},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6184595823287964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6016604900360107},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5329903960227966},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.5087085366249084},{"id":"https://openalex.org/keywords/dynamic-perfect-hashing","display_name":"Dynamic perfect hashing","score":0.48363935947418213},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47008705139160156},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.46679431200027466},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.46435073018074036},{"id":"https://openalex.org/keywords/universal-hashing","display_name":"Universal hashing","score":0.44103389978408813},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4214576482772827},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39009276032447815},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3830878436565399},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.334064781665802},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2743280231952667},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.18582665920257568},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07357937097549438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134889602661133},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6932468414306641},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6184595823287964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6016604900360107},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5329903960227966},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.5087085366249084},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.48363935947418213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47008705139160156},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.46679431200027466},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.46435073018074036},{"id":"https://openalex.org/C116058348","wikidata":"https://www.wikidata.org/wiki/Q846912","display_name":"Universal hashing","level":5,"score":0.44103389978408813},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4214576482772827},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39009276032447815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3830878436565399},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.334064781665802},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2743280231952667},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.18582665920257568},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07357937097549438},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3209978.3210090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209978.3210090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1562412850","https://openalex.org/W1835419070","https://openalex.org/W1959608418","https://openalex.org/W1966093341","https://openalex.org/W1992371516","https://openalex.org/W1999529867","https://openalex.org/W2155482025","https://openalex.org/W2162006472","https://openalex.org/W2293597654","https://openalex.org/W2411707397","https://openalex.org/W2610935556","https://openalex.org/W2740797857","https://openalex.org/W2913932916","https://openalex.org/W2963213486","https://openalex.org/W3212575067","https://openalex.org/W4252076394"],"related_works":["https://openalex.org/W2811247857","https://openalex.org/W102859714","https://openalex.org/W4385382899","https://openalex.org/W2084899141","https://openalex.org/W2044784665","https://openalex.org/W2094127768","https://openalex.org/W1994360333","https://openalex.org/W2334522381","https://openalex.org/W2076162755","https://openalex.org/W4281890709"],"abstract_inverted_index":{"With":[0],"an":[1],"ever":[2],"increasing":[3],"amount":[4],"of":[5,68,83,107],"data":[6,71,86,161],"available":[7],"on":[8,144],"the":[9,16,45,88,98,165],"web,":[10],"fast":[11],"similarity":[12,35],"search":[13],"has":[14,40],"become":[15],"critical":[17],"component":[18],"for":[19,138],"large-scale":[20],"information":[21],"retrieval":[22],"systems.":[23],"One":[24],"solution":[25],"is":[26,87],"semantic":[27,46,62,131,168],"hashing":[28,47,63,94,132,169],"which":[29,72],"designs":[30],"binary":[31,53,155],"codes":[32,54,156],"to":[33,44,56,79,118,134],"accelerate":[34],"search.":[36],"Recently,":[37],"deep":[38,129],"learning":[39,103],"been":[41],"successfully":[42],"applied":[43],"problem":[48],"and":[49,76,162],"produces":[50],"high-quality":[51,154],"compact":[52],"compared":[55],"traditional":[57],"methods.":[58,95],"However,":[59],"most":[60],"state-of-the-art":[61],"approaches":[64],"require":[65],"large":[66],"amounts":[67],"hand-labeled":[69,159],"training":[70,123,160],"are":[73],"often":[74],"expensive":[75],"time":[77],"consuming":[78],"collect.":[80],"The":[81,141],"cost":[82],"getting":[84],"labeled":[85],"key":[89],"bottleneck":[90],"in":[91,101],"deploying":[92],"these":[93],"Motivated":[96],"by":[97],"recent":[99],"success":[100],"machine":[102],"that":[104,149],"makes":[105],"use":[106],"weak":[108,120,136],"supervision,":[109],"we":[110],"employ":[111],"unsupervised":[112,167],"ranking":[113],"methods":[114],"such":[115],"as":[116],"BM25":[117],"extract":[119],"signals":[121,137],"from":[122],"data.":[124],"We":[125],"further":[126],"introduce":[127],"two":[128],"generative":[130],"models":[133,151],"leverage":[135],"text":[139],"hashing.":[140],"experimental":[142],"results":[143],"four":[145],"public":[146],"datasets":[147],"show":[148],"our":[150],"can":[152],"generate":[153],"without":[157],"using":[158],"significantly":[163],"outperform":[164],"competitive":[166],"baselines.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}