{"id":"https://openalex.org/W4385568058","doi":"https://doi.org/10.1145/3580305.3599854","title":"Learning Discrete Document Representations in Web Search","display_name":"Learning Discrete Document Representations in Web Search","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385568058","doi":"https://doi.org/10.1145/3580305.3599854"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599854","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5101617256","display_name":"Rong Huang","orcid":"https://orcid.org/0009-0002-5538-3638"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rong Huang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102970893","display_name":"Danfeng Zhang","orcid":"https://orcid.org/0009-0005-2818-7860"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danfeng Zhang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011022031","display_name":"Weixue Lu","orcid":"https://orcid.org/0000-0003-0761-3419"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixue Lu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814875","display_name":"Han Li","orcid":"https://orcid.org/0009-0002-5044-0664"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Li","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103285762","display_name":"Meng Wang","orcid":"https://orcid.org/0009-0004-4106-4147"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008762356","display_name":"Daiting Shi","orcid":"https://orcid.org/0000-0003-4926-3357"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daiting Shi","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866323","display_name":"Jun Fan","orcid":"https://orcid.org/0009-0000-2127-0702"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Fan","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004991630","display_name":"Zhicong Cheng","orcid":"https://orcid.org/0000-0002-6503-4581"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicong Cheng","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086564536","display_name":"Simiu Gu","orcid":"https://orcid.org/0000-0002-0113-4540"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simiu Gu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101771060","display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-0684-6205"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Yin","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5101617256"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.2456,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5153419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4185","last_page":"4194"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9983000159263611,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980999827384949,"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":0.7694334983825684},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6202202439308167},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6068625450134277},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.508628249168396},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.46557968854904175},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4414155185222626},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.42811036109924316},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4217890501022339},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4212897717952728},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3853866457939148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3796229660511017},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36374157667160034},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1853056252002716},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.11940723657608032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7694334983825684},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6202202439308167},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6068625450134277},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.508628249168396},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.46557968854904175},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4414155185222626},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.42811036109924316},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4217890501022339},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4212897717952728},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3853866457939148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3796229660511017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36374157667160034},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1853056252002716},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.11940723657608032},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599854","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W2077815765","https://openalex.org/W2086179657","https://openalex.org/W2124509324","https://openalex.org/W2738649458","https://openalex.org/W2963265099","https://openalex.org/W2963469388","https://openalex.org/W2964369530","https://openalex.org/W2982512683","https://openalex.org/W2998702515","https://openalex.org/W3034969702","https://openalex.org/W3036320503","https://openalex.org/W3098468692","https://openalex.org/W3145630588","https://openalex.org/W3153624757","https://openalex.org/W3155895380","https://openalex.org/W3156237268","https://openalex.org/W3157758108","https://openalex.org/W3166125679","https://openalex.org/W3172750682","https://openalex.org/W3188983256","https://openalex.org/W3197057826","https://openalex.org/W3198098536","https://openalex.org/W3201037053","https://openalex.org/W3205509771","https://openalex.org/W3209791570","https://openalex.org/W4283797513","https://openalex.org/W4284685333","https://openalex.org/W4290877239","https://openalex.org/W4300011764","https://openalex.org/W6629956336"],"related_works":["https://openalex.org/W2047973478","https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2067569035","https://openalex.org/W2090985514","https://openalex.org/W2885323543","https://openalex.org/W2145649715","https://openalex.org/W2220635983","https://openalex.org/W4307535225","https://openalex.org/W4379381520"],"abstract_inverted_index":{"Product":[0],"quantization":[1],"(PQ)":[2],"has":[3,80],"been":[4],"usually":[5],"applied":[6],"to":[7,14,33,90,101],"dense":[8,44],"retrieval":[9,76,121],"(DR)":[10],"of":[11,61,75],"documents":[12,64],"thanks":[13],"its":[15],"competitive":[16],"time,":[17],"memory":[18],"efficiency":[19],"and":[20,46,88,117],"compatibility":[21],"with":[22,58,108],"other":[23],"approximate":[24],"nearest":[25],"search":[26,127],"(ANN)":[27],"methods.":[28],"Originally,":[29],"PQ":[30,89],"was":[31],"learned":[32],"minimize":[34],"the":[35,39,42,47,59,66,86],"reconstruction":[36],"loss,":[37],"i.e.,":[38],"distortions":[40],"between":[41],"original":[43],"embeddings":[45,49],"reconstructed":[48],"after":[50],"quantization.":[51],"Unfortunately,":[52],"such":[53],"an":[54,103],"objective":[55],"is":[56,98],"inconsistent":[57],"goal":[60],"selecting":[62],"ground-truth":[63],"for":[65,93],"input":[67],"query,":[68],"which":[69],"may":[70],"cause":[71],"a":[72,125],"severe":[73],"loss":[74],"quality.":[77],"Recent":[78],"research":[79],"primarily":[81],"concentrated":[82],"on":[83],"jointly":[84],"training":[85],"biencoders":[87],"ensure":[91],"consistency":[92],"improved":[94],"performance.":[95],"However,":[96],"it":[97],"still":[99],"difficult":[100],"design":[102],"approach":[104],"that":[105],"can":[106],"cope":[107],"challenges":[109],"like":[110],"discrete":[111],"representation":[112],"collapse,":[113],"mining":[114],"informative":[115],"negatives,":[116],"deploying":[118],"effective":[119],"embedding-based":[120],"(EBR)":[122],"systems":[123],"in":[124],"real":[126],"engine.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}