{"id":"https://openalex.org/W1861351285","doi":"https://doi.org/10.1145/2487788.2487849","title":"An error driven approach to query segmentation","display_name":"An error driven approach to query segmentation","publication_year":2013,"publication_date":"2013-05-13","ids":{"openalex":"https://openalex.org/W1861351285","doi":"https://doi.org/10.1145/2487788.2487849","mag":"1861351285"},"language":"en","primary_location":{"id":"doi:10.1145/2487788.2487849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487788.2487849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on World Wide Web","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/A5000814233","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-0195-2666"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Institute for Infocomm Research, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011542448","display_name":"Yunbo Cao","orcid":"https://orcid.org/0009-0005-2558-5206"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Cao","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090151187","display_name":"Chin-Yew Lin","orcid":"https://orcid.org/0000-0002-0798-6365"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chin-Yew Lin","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101860993","display_name":"Jian Su","orcid":"https://orcid.org/0009-0001-9484-5885"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jian Su","raw_affiliation_strings":["Institute for Infocomm Research, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108376447","display_name":"Chew-Lim Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chew-Lim Tan","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9961000084877014,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8208310604095459},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7329314947128296},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.6471469402313232},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.6374707818031311},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6058910489082336},{"id":"https://openalex.org/keywords/online-aggregation","display_name":"Online aggregation","score":0.570681631565094},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5626341700553894},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.5390794277191162},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.5333635210990906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45740652084350586},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4472719132900238},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4336532950401306},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.41966119408607483},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40891581773757935},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3740321397781372},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34491539001464844},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3051454424858093},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.1754860281944275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8208310604095459},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7329314947128296},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.6471469402313232},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.6374707818031311},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6058910489082336},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.570681631565094},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5626341700553894},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.5390794277191162},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.5333635210990906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45740652084350586},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4472719132900238},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4336532950401306},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.41966119408607483},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40891581773757935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3740321397781372},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34491539001464844},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3051454424858093},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.1754860281944275},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2487788.2487849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487788.2487849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/78010","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/78010","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.309.7436","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.309.7436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/~tancl/publications/c2013/p127.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.359.9718","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.359.9718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.iitb.ac.in/~soumen/doc/www2013/QirWoo/ZhangCLST2013ErrorDrivenQuerySegment.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1972070683","https://openalex.org/W2087198174","https://openalex.org/W2117424365","https://openalex.org/W2141335422","https://openalex.org/W6677618753","https://openalex.org/W6680963280"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W3125756434","https://openalex.org/W2901901036","https://openalex.org/W1560919561","https://openalex.org/W1793997780","https://openalex.org/W2013069866","https://openalex.org/W2150741898","https://openalex.org/W185198413","https://openalex.org/W2538384344","https://openalex.org/W2168049757"],"abstract_inverted_index":{"Query":[0],"segmentation":[1,27,41,90,116],"is":[2,80],"the":[3,21,44,56,64,69,72,83,88,96,100,111],"task":[4],"of":[5,12,25,46,74,91,99,113],"splitting":[6],"a":[7,10,78,92,119],"query":[8,26,40,94,115],"into":[9],"sequence":[11],"non-overlapping":[13],"segments":[14],"that":[15,106],"completely":[16],"cover":[17],"all":[18],"tokens":[19],"in":[20],"query.":[22],"The":[23],"majority":[24],"methods":[28,117],"are":[29],"unsupervised.":[30],"In":[31,59],"this":[32],"paper,":[33],"we":[34,61],"propose":[35],"an":[36],"error-driven":[37],"approach":[38],"to":[39,86],"(EDQS)":[42],"with":[43,53],"help":[45],"search":[47],"logs,":[48],"which":[49],"enables":[50],"unsupervised":[51],"training":[52],"guidance":[54],"from":[55,95],"system-specific":[57],"errors.":[58],"EDQS,":[60],"first":[62],"detect":[63],"system's":[65],"errors":[66,85],"by":[67,82],"examining":[68],"consistency":[70],"among":[71],"segmentations":[73],"similar":[75],"queries.":[76],"Then,":[77],"model":[79],"trained":[81],"detected":[84],"select":[87],"correct":[89],"new":[93],"top-n":[97],"outputs":[98],"system.":[101],"Our":[102],"evaluation":[103],"results":[104],"show":[105],"EDQS":[107],"can":[108],"significantly":[109],"boost":[110],"performance":[112],"state-of-the-art":[114],"on":[118],"publicly":[120],"available":[121],"data":[122],"set.":[123]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}