{"id":"https://openalex.org/W7163685750","doi":"https://doi.org/10.1145/3805712.3808520","title":"BEATS: Bootstrapping E-commerce Attribute Taxonomies for Search through Iterative Human-AI Collaboration","display_name":"BEATS: Bootstrapping E-commerce Attribute Taxonomies for Search through Iterative Human-AI Collaboration","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7163685750","doi":"https://doi.org/10.1145/3805712.3808520"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808520","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808520","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808520","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066864218","display_name":"Yung-Yu Shih","orcid":"https://orcid.org/0009-0003-5194-8803"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yung-Yu Shih","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0003-5194-8803","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137917585","display_name":"Shang-Yu Su","orcid":null},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shang-Yu Su","raw_affiliation_strings":["Rakuten Group Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4313-6066","affiliations":[{"raw_affiliation_string":"Rakuten Group Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I1301041018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010850053","display_name":"Tzu-I Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164442","display_name":"Dharma Drum Institute of Liberal Arts","ror":"https://ror.org/05hkpfm52","country_code":"TW","type":"education","lineage":["https://openalex.org/I4210164442"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tzu-I Ho","raw_affiliation_strings":["Taiwan Rakuten Ichiba Inc., Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0000-2972-8845","affiliations":[{"raw_affiliation_string":"Taiwan Rakuten Ichiba Inc., Taipei, Taiwan","institution_ids":["https://openalex.org/I4210164442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041201587","display_name":"Dongzhe Wang","orcid":"https://orcid.org/0000-0002-1467-6023"},"institutions":[{"id":"https://openalex.org/I4210155759","display_name":"Merck (Singapore)","ror":"https://ror.org/05cq2am04","country_code":"SG","type":"company","lineage":["https://openalex.org/I4210155759"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dongzhe Wang","raw_affiliation_strings":["Rakuten Asia Pte. Ltd., Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1467-6023","affiliations":[{"raw_affiliation_string":"Rakuten Asia Pte. Ltd., Singapore, Singapore","institution_ids":["https://openalex.org/I4210155759"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138014065","display_name":"Yun-Nung Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yun-Nung Chen","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-1777-3942","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63293588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4874","last_page":"4879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.4715000092983246,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.4715000092983246,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.07970000058412552,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.04670000076293945,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/ranking","display_name":"Ranking (information retrieval)","score":0.5291000008583069},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5181000232696533},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5126000046730042},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.4625000059604645},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4625000059604645},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4433000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119999766349792},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.588100016117096},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805712.3808520","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808520","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.04909","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.04909","pdf_url":"https://arxiv.org/pdf/2606.04909","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808520","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808520","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41890794038772583},{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.40594232082366943}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"E-commerce":[0],"platforms":[1],"in":[2],"emerging":[3],"markets":[4],"often":[5],"operate":[6],"with":[7,66,207,219,223],"underdeveloped":[8],"product":[9,25,52,135,181,229],"catalogs":[10],"that":[11],"contain":[12],"only":[13],"category":[14],"taxonomies":[15,54],"but":[16],"lack":[17],"structured":[18,130,157],"attribute":[19,53,117,121,131],"schemas.":[20],"This":[21],"absence":[22],"of":[23,148],"fine-grained":[24],"attributes":[26],"limits":[27],"search":[28,41,150],"capabilities---preventing":[29],"faceted":[30],"filtering,":[31,155],"degrading":[32],"query":[33],"understanding,":[34],"and":[35,82,109,162,211],"weakening":[36],"semantic":[37,164],"representations":[38,165],"used":[39],"by":[40,75,86,174],"systems.":[42],"We":[43,169],"present":[44],"BEATS,":[45],"a":[46,61],"human-in-the-loop":[47],"LLM":[48,63],"framework":[49,95],"for":[50,159,166],"bootstrapping":[51],"entirely":[55],"from":[56],"scratch.":[57],"Our":[58,192],"approach":[59],"extends":[60],"multi-stage":[62],"generation":[64,100],"pipeline":[65],"two":[67],"critical":[68],"production":[69],"stages:":[70],"(1)":[71],"proactive":[72],"quality":[73,106],"checking":[74],"model":[76],"developers":[77],"to":[78,90,128,225],"filter":[79],"erroneous":[80],"outputs,":[81],"(2)":[83],"human":[84],"annotation":[85],"domain-expert":[87],"local":[88],"staff":[89],"validate":[91,170],"generated":[92,172,209,221],"attributes.":[93],"The":[94,141],"operates":[96],"iteratively---prompts":[97],"at":[98,197],"each":[99],"stage":[101],"are":[102],"refined":[103],"based":[104],"on":[105,133,179],"check":[107],"observations":[108],"annotator":[110],"feedback":[111],"across":[112],"successive":[113],"rounds,":[114],"progressively":[115],"improving":[116,163],"quality.":[118],"Once":[119],"the":[120,149,171,220,227],"taxonomy":[122,173],"is":[123],"established,":[124],"we":[125],"employ":[126],"LLMs":[127],"perform":[129],"tagging":[132],"individual":[134],"items,":[136],"enriching":[137,200],"their":[138],"contextual":[139],"representations.":[140],"enriched":[142],"catalog":[143,190],"directly":[144],"benefits":[145],"multiple":[146],"components":[147],"system:":[151],"enabling":[152],"granular":[153],"attribute-based":[154],"providing":[156],"features":[158],"ranking":[160],"models,":[161],"dense":[167,176],"retrieval.":[168],"training":[175],"retrieval":[177],"models":[178],"attribute-enriched":[180],"data,":[182],"demonstrating":[183],"consistent":[184],"improvements":[185],"over":[186,212],"baselines":[187],"using":[188],"original":[189],"information.":[191],"system":[193],"has":[194],"been":[195,217],"deployed":[196],"Rakuten":[198],"Taiwan,":[199],"9":[201],"major":[202],"categories":[203],"spanning":[204],"2,694":[205],"sub-categories":[206],"67,277":[208],"attributes,":[210,222],"5.4":[213],"million":[214],"products":[215],"have":[216],"tagged":[218],"plans":[224],"enrich":[226],"entire":[228],"catalog.":[230]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-06-06T00:00:00"}