{"id":"https://openalex.org/W1075889387","doi":"https://doi.org/10.1145/2740908.2741995","title":"Search Query Categorization at Scale","display_name":"Search Query Categorization at Scale","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W1075889387","doi":"https://doi.org/10.1145/2740908.2741995","mag":"1075889387"},"language":"en","primary_location":{"id":"doi:10.1145/2740908.2741995","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2741995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","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/A5001388235","display_name":"Michal Laclav\u00edk","orcid":"https://orcid.org/0000-0002-6634-5832"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Michal Laclavik","raw_affiliation_strings":["Magnetic Media Online, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Magnetic Media Online, New York, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004255004","display_name":"Marek Ciglan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marek Ciglan","raw_affiliation_strings":["Magnetic Media Online, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Magnetic Media Online, New York, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051548297","display_name":"Sam Steingold","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Steingold","raw_affiliation_strings":["Magnetic Media Online, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Magnetic Media Online, New York, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005702571","display_name":"Martin \u0160eleng","orcid":"https://orcid.org/0000-0002-4026-6095"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I207624831","display_name":"Slovak Academy of Sciences","ror":"https://ror.org/03h7qq074","country_code":"SK","type":"funder","lineage":["https://openalex.org/I207624831"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Martin Seleng","raw_affiliation_strings":["Institute of Informatics, Slovak Academy of Sciences, Bratislava, Slovakia"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Slovak Academy of Sciences, Bratislava, Slovakia","institution_ids":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020786891","display_name":"Alex Dorman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Dorman","raw_affiliation_strings":["Magnetic Media Online, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Magnetic Media Online, New York, NY, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061630089","display_name":"\u0160tefan Dlugolinsk\u00fd","orcid":"https://orcid.org/0000-0002-4424-4221"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I207624831","display_name":"Slovak Academy of Sciences","ror":"https://ror.org/03h7qq074","country_code":"SK","type":"funder","lineage":["https://openalex.org/I207624831"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Stefan Dlugolinsky","raw_affiliation_strings":["Institute of Informatics, Slovak Academy of Sciences, Bratislava, Slovakia"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Slovak Academy of Sciences, Bratislava, Slovakia","institution_ids":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001388235"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7258,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87577433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1281","last_page":"1286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9836000204086304,"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":0.9829000234603882,"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":0.873471736907959},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7630525827407837},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7482987642288208},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.7021727561950684},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.6856834888458252},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6709515452384949},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5443678498268127},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.49425792694091797},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.46357041597366333},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46284031867980957},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.43766599893569946},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3463730812072754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2650600075721741},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16454541683197021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.873471736907959},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7630525827407837},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7482987642288208},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.7021727561950684},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.6856834888458252},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6709515452384949},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5443678498268127},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.49425792694091797},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.46357041597366333},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46284031867980957},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.43766599893569946},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3463730812072754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2650600075721741},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16454541683197021},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2740908.2741995","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2741995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1541557452","https://openalex.org/W1549023374","https://openalex.org/W1965325733","https://openalex.org/W1997189720","https://openalex.org/W1998548536","https://openalex.org/W2034927834","https://openalex.org/W2102029756","https://openalex.org/W2134606514","https://openalex.org/W2145565903","https://openalex.org/W2400170782"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2901901036","https://openalex.org/W2026738364","https://openalex.org/W1521725692","https://openalex.org/W2093300859","https://openalex.org/W3008917487","https://openalex.org/W2124814993","https://openalex.org/W2013069866","https://openalex.org/W3197639690","https://openalex.org/W2572349046"],"abstract_inverted_index":{"State":[0],"of":[1,26,74],"the":[2,14,87,103,108,119,135,149],"art":[3],"query":[4,99],"categorization":[5,73,132],"methods":[6],"usually":[7],"exploit":[8],"web":[9,17,39,48],"search":[10,49,75,125],"services":[11],"to":[12,22,43,72,102,148],"retrieve":[13],"best":[15],"matching":[16],"documents":[18,110],"and":[19,41,57,69,127,156],"map":[20],"them":[21],"a":[23,38,45,66,79,98,114,129,139],"given":[24,115],"taxonomy":[25],"categories.":[27],"This":[28],"is":[29,100],"effective":[30],"but":[31],"impractical":[32],"when":[33],"one":[34],"does":[35],"not":[36],"own":[37],"corpus":[40],"has":[42],"use":[44,84],"3rd":[46],"party":[47],"engine":[50],"API.":[51],"The":[52,90],"problem":[53,126],"lies":[54],"in":[55,58],"performance":[56,155],"financial":[59],"costs.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,83],"present":[65,128],"novel,":[67],"fast":[68],"scalable":[70],"approach":[71,118,133,144],"queries":[76],"based":[77],"on":[78,94],"limited":[80],"intermediate":[81],"corpus:":[82],"Wikipedia":[85,105],"as":[86,122],"knowledge":[88],"base.":[89],"presented":[91],"solution":[92],"relies":[93],"two":[95],"steps:":[96],"first":[97,120],"mapped":[101],"relevant":[104],"pages;":[106],"second,":[107],"retrieved":[109],"are":[111],"categorized":[112],"into":[113],"taxonomy.":[116],"We":[117],"challenge":[121],"an":[123],"entity":[124],"new":[130],"document":[131],"for":[134],"second":[136],"step.":[137],"On":[138],"standard":[140],"data":[141],"set,":[142],"our":[143],"achieves":[145],"results":[146],"comparable":[147],"state-of-the-art":[150],"approaches":[151],"while":[152],"maintaining":[153],"high":[154],"scalability.":[157]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
