{"id":"https://openalex.org/W4378472638","doi":"https://doi.org/10.1007/978-3-031-33380-4_6","title":"Web-Scale Semantic Product Search with\u00a0Large Language Models","display_name":"Web-Scale Semantic Product Search with\u00a0Large Language Models","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4378472638","doi":"https://doi.org/10.1007/978-3-031-33380-4_6"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-33380-4_6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-33380-4_6","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-33380-4_6.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-33380-4_6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082273313","display_name":"Aashiq Muhamed","orcid":"https://orcid.org/0000-0002-8657-0439"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aashiq Muhamed","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101516752","display_name":"Sriram Srinivasan","orcid":"https://orcid.org/0009-0000-7487-3638"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Srinivasan","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067754381","display_name":"Choon-Hui Teo","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Choon-Hui Teo","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068272021","display_name":"Qingjun Cui","orcid":"https://orcid.org/0000-0002-6600-9804"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingjun Cui","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082750097","display_name":"Belinda Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Belinda Zeng","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013670321","display_name":"Trishul Chilimbi","orcid":"https://orcid.org/0000-0001-6711-1117"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trishul Chilimbi","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013623933","display_name":"S. V. N. Vishwanathan","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. V. N. Vishwanathan","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5082273313"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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/T11550","display_name":"Text and Document Classification Technologies","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":0.8797928094863892},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6579875349998474},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6048651337623596},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5453247427940369},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4994699954986572},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48028990626335144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47942274808883667},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4448942542076111},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43256497383117676},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.41077035665512085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3924816846847534},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3672257661819458},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35590386390686035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8797928094863892},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6579875349998474},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6048651337623596},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5453247427940369},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4994699954986572},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48028990626335144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47942274808883667},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4448942542076111},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43256497383117676},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.41077035665512085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3924816846847534},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3672257661819458},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35590386390686035},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-33380-4_6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-33380-4_6","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-33380-4_6.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-33380-4_6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-33380-4_6","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-33380-4_6.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378472638.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2136189984","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2963469388","https://openalex.org/W2964369530","https://openalex.org/W2970641574","https://openalex.org/W3021397474","https://openalex.org/W3035390927","https://openalex.org/W3036320503","https://openalex.org/W3038572442","https://openalex.org/W3094444847","https://openalex.org/W3098468692","https://openalex.org/W3099700870","https://openalex.org/W3166125679","https://openalex.org/W3172750682","https://openalex.org/W4213009331"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4390516098","https://openalex.org/W2037549926","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2142795561","https://openalex.org/W2849310602","https://openalex.org/W4205302943"],"abstract_inverted_index":{"Abstract":[0],"Dense":[1],"embedding-based":[2],"semantic":[3],"matching":[4,18,116],"is":[5],"widely":[6],"used":[7],"in":[8,28,168,194],"e-commerce":[9,51,125],"product":[10,98,126],"search":[11,41,99,144],"to":[12,22,39,43,73,92,110,149,172],"address":[13],"the":[14,44,77,143,173,191],"shortcomings":[15],"of":[16],"lexical":[17],"such":[19],"as":[20],"sensitivity":[21],"spelling":[23],"variants.":[24],"The":[25,160],"recent":[26],"advances":[27],"BERT-like":[29,95],"language":[30],"model":[31,135,155,162,193],"encoders,":[32],"have":[33],"however,":[34],"not":[35],"found":[36],"their":[37],"way":[38],"realtime":[40],"due":[42,72],"strict":[45],"inference":[46,103,158],"latency":[47],"requirement":[48],"imposed":[49],"on":[50,66,123],"websites.":[52],"While":[53],"bi-encoder":[54],"BERT":[55,113],"architectures":[56],"enable":[57],"fast":[58],"approximate":[59],"nearest":[60],"neighbor":[61],"search,":[62],"training":[63,74,90],"them":[64],"effectively":[65,111],"query-product":[67,107],"data":[68],"remains":[69],"a":[70,88,131,152,165],"challenge":[71],"instabilities":[75],"and":[76,117,196],"persistent":[78],"generalization":[79],"gap":[80],"with":[81,156],"cross-encoders.":[82],"In":[83],"this":[84],"work,":[85],"we":[86,128],"propose":[87],"four-stage":[89],"procedure":[91],"leverage":[93],"large":[94],"models":[96],"for":[97,115],"while":[100],"preserving":[101],"low":[102],"latency.":[104,159],"We":[105,177],"introduce":[106],"interaction":[108],"pre-finetuning":[109],"pretrain":[112],"bi-encoders":[114],"improve":[118],"generalization.":[119],"Through":[120],"offline":[121],"experiments":[122],"an":[124],"dataset,":[127],"show":[129,179],"that":[130,186],"distilled":[132],"small":[133,161],"BERT-based":[134],"(75M":[136],"params)":[137],"trained":[138],"using":[139,180],"our":[140,187],"approach":[141,188],"improves":[142,189],"relevance":[145,169],"metric":[146,170],"by":[147],"up":[148],"23%":[150],"over":[151,190],"baseline":[153],"DSSM-based":[154],"similar":[157],"only":[163],"suffers":[164],"3%":[166],"drop":[167],"compared":[171],"20x":[174],"larger":[175],"teacher.":[176],"also":[178],"online":[181],"A/B":[182],"tests":[183],"at":[184],"scale,":[185],"production":[192],"exact":[195],"substitute":[197],"products":[198],"retrieved.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}