{"id":"https://openalex.org/W2026449615","doi":"https://doi.org/10.1145/2124295.2124342","title":"Sequence clustering and labeling for unsupervised query intent discovery","display_name":"Sequence clustering and labeling for unsupervised query intent discovery","publication_year":2012,"publication_date":"2012-02-08","ids":{"openalex":"https://openalex.org/W2026449615","doi":"https://doi.org/10.1145/2124295.2124342","mag":"2026449615"},"language":"en","primary_location":{"id":"doi:10.1145/2124295.2124342","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2124295.2124342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5050801868","display_name":"Jackie Chi Kit Cheung","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jackie Chi Kit Cheung","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada","University of Toronto, Toronto, On, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Toronto, On, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100755904","display_name":"Xiao Li","orcid":"https://orcid.org/0000-0002-2406-3781"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Li","raw_affiliation_strings":["Facebook Inc., Palo Alto, CA, USA","Facebook, Inc., Palo Alto, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc., Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook, Inc., Palo Alto, CA, USA#TAB#","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8585158586502075},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6788003444671631},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6542074680328369},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5836664438247681},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5104030966758728},{"id":"https://openalex.org/keywords/semantic-search","display_name":"Semantic search","score":0.4813271760940552},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.4323662519454956},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34202343225479126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3145049810409546},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.29569923877716064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8585158586502075},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6788003444671631},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6542074680328369},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5836664438247681},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5104030966758728},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.4813271760940552},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.4323662519454956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34202343225479126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3145049810409546},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.29569923877716064}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2124295.2124342","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2124295.2124342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.225.1823","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.225.1823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utoronto.ca/%7Ejcheung/papers/wsdm2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W69597389","https://openalex.org/W112197792","https://openalex.org/W167355512","https://openalex.org/W1532325895","https://openalex.org/W1560013842","https://openalex.org/W1564094940","https://openalex.org/W1599399636","https://openalex.org/W1970832239","https://openalex.org/W1972645849","https://openalex.org/W1973867972","https://openalex.org/W1988152160","https://openalex.org/W1992419399","https://openalex.org/W2047032662","https://openalex.org/W2068737686","https://openalex.org/W2088762045","https://openalex.org/W2096956703","https://openalex.org/W2098019918","https://openalex.org/W2098700435","https://openalex.org/W2100328374","https://openalex.org/W2105540829","https://openalex.org/W2105649185","https://openalex.org/W2110360823","https://openalex.org/W2123131857","https://openalex.org/W2124634352","https://openalex.org/W2144108169","https://openalex.org/W2146446188","https://openalex.org/W2158345769","https://openalex.org/W2162235411","https://openalex.org/W2171683557","https://openalex.org/W2337759341","https://openalex.org/W2536379393","https://openalex.org/W2882319491","https://openalex.org/W2886362482","https://openalex.org/W4297974288","https://openalex.org/W6602823196","https://openalex.org/W6753056052"],"related_works":["https://openalex.org/W2185998359","https://openalex.org/W218333555","https://openalex.org/W2262062475","https://openalex.org/W2186976797","https://openalex.org/W1760324756","https://openalex.org/W2093311372","https://openalex.org/W1926636715","https://openalex.org/W979688644","https://openalex.org/W2940786036","https://openalex.org/W2111960202"],"abstract_inverted_index":{"One":[0],"popular":[1],"form":[2],"of":[3,41,102,105,127,161,165,177],"semantic":[4,106],"search":[5,10,27,67],"observed":[6],"in":[7,36,45,55,132],"several":[8],"modern":[9],"engines":[11],"is":[12,58],"to":[13,38,47,59,65,77,121,171],"recognize":[14],"query":[15,34,43],"patterns":[16,120,146,162],"that":[17,76,158],"trigger":[18],"instant":[19],"answers":[20],"or":[21],"domain-specific":[22],"search,":[23],"producing":[24,98],"semantically":[25],"enriched":[26],"results.":[28],"This":[29],"often":[30],"requires":[31],"understanding":[32,57],"the":[33,39,42,117],"intent":[35,56,95,119,145],"addition":[37],"meaning":[40],"terms":[44],"order":[46],"access":[48],"structured":[49],"data":[50],"sources.":[51],"A":[52],"major":[53],"challenge":[54],"construct":[60],"a":[61,72,74,99,103,124,175],"domain-dependent":[62],"schema":[63],"and":[64,96,147,163],"annotate":[66,123],"queries":[68,92,128],"based":[69],"on":[70,138],"such":[71],"schema,":[73],"process":[75],"date":[78],"has":[79],"required":[80],"much":[81],"manual":[82],"annotation":[83],"effort.":[84],"We":[85,134,156],"present":[86],"an":[87],"unsupervised":[88],"method":[89,137],"for":[90,97,111],"clustering":[91],"with":[93],"similar":[94],"pattern":[100],"consisting":[101],"sequence":[104],"concepts":[107],"and/or":[108],"lexical":[109],"items":[110],"each":[112],"intent.":[113],"Furthermore,":[114],"we":[115],"leverage":[116],"discovered":[118],"automatically":[122,148],"large":[125],"number":[126],"beyond":[129],"those":[130],"used":[131],"clustering.":[133],"evaluated":[135],"our":[136],"10":[139],"selected":[140],"domains,":[141],"discovering":[142],"over":[143,159],"1400":[144],"annotating":[149],"125K":[150],"(and":[151],"potentially":[152],"many":[153],"more)":[154],"queries.":[155],"found":[157],"90%":[160],"80%":[164],"instance":[166],"annotations":[167],"tested":[168],"are":[169],"judged":[170],"be":[172],"correct":[173],"by":[174],"majority":[176],"annotators.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}