{"id":"https://openalex.org/W4321648515","doi":"https://doi.org/10.1145/3543873.3584622","title":"HierCat: Hierarchical Query Categorization from Weakly Supervised Data at Facebook Marketplace","display_name":"HierCat: Hierarchical Query Categorization from Weakly Supervised Data at Facebook Marketplace","publication_year":2023,"publication_date":"2023-04-28","ids":{"openalex":"https://openalex.org/W4321648515","doi":"https://doi.org/10.1145/3543873.3584622"},"language":"en","primary_location":{"id":"doi:10.1145/3543873.3584622","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543873.3584622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.10527","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079019876","display_name":"Yunzhong He","orcid":"https://orcid.org/0000-0002-5429-5372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunzhong He","raw_affiliation_strings":["Meta, USA"],"raw_orcid":"https://orcid.org/0000-0002-5429-5372","affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438369","display_name":"Cong Zhang","orcid":"https://orcid.org/0000-0001-8339-7709"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Zhang","raw_affiliation_strings":["Meta, USA"],"raw_orcid":"https://orcid.org/0000-0001-8339-7709","affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031976235","display_name":"Ruoyan Kong","orcid":"https://orcid.org/0000-0003-0585-0453"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruoyan Kong","raw_affiliation_strings":["University of Minnesota Twin Cities, USA"],"raw_orcid":"https://orcid.org/0000-0003-0585-0453","affiliations":[{"raw_affiliation_string":"University of Minnesota Twin Cities, USA","institution_ids":["https://openalex.org/I4210101327","https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101958981","display_name":"Chaitanya Kulkarni","orcid":"https://orcid.org/0000-0002-6130-2016"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaitanya Kulkarni","raw_affiliation_strings":["Meta, USA"],"raw_orcid":"https://orcid.org/0000-0002-6130-2016","affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030584506","display_name":"Qing Liu","orcid":"https://orcid.org/0000-0003-4651-654X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Liu","raw_affiliation_strings":["Meta, USA"],"raw_orcid":"https://orcid.org/0000-0003-4651-654X","affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012984945","display_name":"A. Gandhe","orcid":"https://orcid.org/0000-0002-8808-1014"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Gandhe","raw_affiliation_strings":["Meta, USA"],"raw_orcid":"https://orcid.org/0000-0002-8808-1014","affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072015070","display_name":"Amit Nithianandan","orcid":"https://orcid.org/0000-0002-0674-6618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amit Nithianandan","raw_affiliation_strings":["Meta, USA"],"raw_orcid":"https://orcid.org/0000-0002-0674-6618","affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031401345","display_name":"Arul Prakash","orcid":"https://orcid.org/0000-0002-0651-7145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arul Prakash","raw_affiliation_strings":["Meta, USA"],"raw_orcid":"https://orcid.org/0000-0002-0651-7145","affiliations":[{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9592,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78175449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9980999827384949,"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.8503484725952148},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.6542943716049194},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5810403227806091},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.568790078163147},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5620100498199463},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5536195635795593},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5520883798599243},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5318142175674438},{"id":"https://openalex.org/keywords/vagueness","display_name":"Vagueness","score":0.4501972198486328},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.448845237493515},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4152563512325287},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3942982256412506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.375210702419281},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.36164698004722595},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20503056049346924},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09399521350860596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8503484725952148},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.6542943716049194},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5810403227806091},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.568790078163147},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5620100498199463},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5536195635795593},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5520883798599243},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5318142175674438},{"id":"https://openalex.org/C2776825360","wikidata":"https://www.wikidata.org/wiki/Q1411921","display_name":"Vagueness","level":3,"score":0.4501972198486328},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.448845237493515},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4152563512325287},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3942982256412506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.375210702419281},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.36164698004722595},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20503056049346924},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09399521350860596},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3543873.3584622","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543873.3584622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2302.10527","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.10527","pdf_url":"https://arxiv.org/pdf/2302.10527","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.10527","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.10527","pdf_url":"https://arxiv.org/pdf/2302.10527","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4321648515.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1987700483","https://openalex.org/W2141880913","https://openalex.org/W2493916176","https://openalex.org/W2528321558","https://openalex.org/W2739996966","https://openalex.org/W2794670651","https://openalex.org/W2899771611","https://openalex.org/W2963626623","https://openalex.org/W2964812254","https://openalex.org/W2965839155","https://openalex.org/W2989224055","https://openalex.org/W3035390927","https://openalex.org/W3035523710","https://openalex.org/W3156781964","https://openalex.org/W3167329294"],"related_works":["https://openalex.org/W2964061033","https://openalex.org/W3127142483","https://openalex.org/W4385565564","https://openalex.org/W2898073868","https://openalex.org/W2138488530","https://openalex.org/W4390446658","https://openalex.org/W2971071571","https://openalex.org/W2798835721","https://openalex.org/W2922169395","https://openalex.org/W2387658907"],"abstract_inverted_index":{"Query":[0],"categorization":[1,59],"at":[2,61,118],"customer-to-customer":[3],"e-commerce":[4],"platforms":[5],"like":[6],"Facebook":[7,62,119],"Marketplace":[8,120],"is":[9],"challenging":[10],"due":[11],"to":[12,32,42,80,107],"the":[13,57],"vagueness":[14],"of":[15,72,125],"search":[16,48],"intent,":[17],"noise":[18],"in":[19,35,40,101,110,115,122],"real-world":[20],"data,":[21],"and":[22,37,112],"imbalanced":[23],"training":[24,86],"data":[25,87],"across":[26],"languages.":[27],"Its":[28],"deployment":[29],"also":[30,105],"needs":[31],"consider":[33],"challenges":[34,67],"scalability":[36],"downstream":[38],"integration":[39],"order":[41],"translate":[43],"modeling":[44],"advances":[45],"into":[46],"better":[47],"result":[49],"relevance.":[50],"In":[51],"this":[52],"paper":[53],"we":[54],"present":[55],"HierCat,":[56],"query":[58],"system":[60],"Marketplace.":[63],"HierCat":[64,95],"addresses":[65],"these":[66],"by":[68],"leveraging":[69],"multi-task":[70],"pre-training":[71],"dual-encoder":[73],"architectures":[74],"with":[75],"a":[76],"hierarchical":[77],"inference":[78],"step":[79],"effectively":[81],"learn":[82],"from":[83,89],"weakly":[84],"supervised":[85],"mined":[88],"searcher":[90,116],"engagement.":[91],"We":[92],"show":[93],"that":[94],"not":[96],"only":[97],"outperforms":[98],"popular":[99],"methods":[100],"offline":[102],"experiments,":[103],"but":[104],"leads":[106],"1.4%":[108],"improvement":[109],"NDCG":[111],"4.3%":[113],"increase":[114],"engagement":[117],"Search":[121],"two":[123],"weeks":[124],"online":[126],"A/B":[127],"testing.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2023-02-24T00:00:00"}