{"id":"https://openalex.org/W2103196492","doi":"https://doi.org/10.1145/1963192.1963239","title":"Unsupervised query segmentation using only query logs","display_name":"Unsupervised query segmentation using only query logs","publication_year":2011,"publication_date":"2011-03-28","ids":{"openalex":"https://openalex.org/W2103196492","doi":"https://doi.org/10.1145/1963192.1963239","mag":"2103196492"},"language":"en","primary_location":{"id":"doi:10.1145/1963192.1963239","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963192.1963239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international conference companion 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/A5019688465","display_name":"Nikita Mishra","orcid":"https://orcid.org/0000-0002-4226-6742"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nikita Mishra","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, Kharagpur, India","Indian Institute of Technology Kharagpur, Kharagpur, India;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, India;","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042165238","display_name":"Rishiraj Saha Roy","orcid":"https://orcid.org/0000-0002-5774-5658"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rishiraj Saha Roy","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, Kharagpur, India","Indian Institute of Technology Kharagpur, Kharagpur, India;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, India;","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073812421","display_name":"Niloy Ganguly","orcid":"https://orcid.org/0000-0002-3967-186X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Niloy Ganguly","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, Kharagpur, India","Indian Institute of Technology Kharagpur, Kharagpur, India;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, India;","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050748800","display_name":"Srivatsan Laxman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Srivatsan Laxman","raw_affiliation_strings":["Microsoft Research India, Bengaluru, India","Microsoft Research India, Bengaluru, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India, Bengaluru, India","institution_ids":["https://openalex.org/I4210124949"]},{"raw_affiliation_string":"Microsoft Research India, Bengaluru, India#TAB#","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008944385","display_name":"Monojit Choudhury","orcid":"https://orcid.org/0000-0001-7473-7839"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Monojit Choudhury","raw_affiliation_strings":["Microsoft Research India, Bengaluru, India","Microsoft Research India, Bengaluru, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India, Bengaluru, India","institution_ids":["https://openalex.org/I4210124949"]},{"raw_affiliation_string":"Microsoft Research India, Bengaluru, India#TAB#","institution_ids":["https://openalex.org/I4210124949"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5862,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95813328,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.998199999332428,"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/T11269","display_name":"Algorithms and Data Compression","score":0.998199999332428,"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":0.9980000257492065,"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/T11106","display_name":"Data Management and Algorithms","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8155912160873413},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6419637203216553},{"id":"https://openalex.org/keywords/pointwise-mutual-information","display_name":"Pointwise mutual information","score":0.5845377445220947},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.5783300399780273},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.5763272643089294},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.537243127822876},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5327950119972229},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5221182107925415},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.5059983134269714},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4995462894439697},{"id":"https://openalex.org/keywords/rdf-query-language","display_name":"RDF query language","score":0.4839823246002197},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.4741748571395874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45853811502456665},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4359561800956726},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3682310879230499},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.23594346642494202},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.21877974271774292},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08595240116119385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155912160873413},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6419637203216553},{"id":"https://openalex.org/C7797323","wikidata":"https://www.wikidata.org/wiki/Q3798612","display_name":"Pointwise mutual information","level":3,"score":0.5845377445220947},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.5783300399780273},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.5763272643089294},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.537243127822876},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5327950119972229},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5221182107925415},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.5059983134269714},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4995462894439697},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.4839823246002197},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.4741748571395874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45853811502456665},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4359561800956726},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3682310879230499},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.23594346642494202},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.21877974271774292},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08595240116119385},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1963192.1963239","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963192.1963239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international conference companion on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.8232","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.8232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2011india.com/proceeding/companion/p91.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.723.6550","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.723.6550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.facweb.iitkgp.ernet.in/%7Eniloy/PAPER/Rishi.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1852047886","https://openalex.org/W2098700435","https://openalex.org/W2117424365","https://openalex.org/W2141335422","https://openalex.org/W2423725643"],"related_works":["https://openalex.org/W2572349046","https://openalex.org/W2096359267","https://openalex.org/W2169498276","https://openalex.org/W2146885082","https://openalex.org/W2392799717","https://openalex.org/W2026738364","https://openalex.org/W1984397732","https://openalex.org/W5304494","https://openalex.org/W2017989738","https://openalex.org/W2029593518"],"abstract_inverted_index":{"We":[0,24,58],"introduce":[1],"an":[2],"unsupervised":[3],"query":[4,9],"segmentation":[5],"scheme":[6,51],"that":[7,26,39,88,95],"uses":[8],"logs":[10],"as":[11],"the":[12,19,80],"only":[13],"resource":[14],"and":[15,74],"can":[16,91],"effectively":[17],"capture":[18],"structural":[20],"units":[21,94],"in":[22],"queries.":[23,81],"believe":[25],"Web":[27],"search":[28],"queries":[29,73,86],"have":[30],"a":[31,43,60],"unique":[32],"syntactic":[33],"structure":[34],"which":[35],"is":[36],"distinct":[37],"from":[38,72],"of":[40],"English":[41],"or":[42],"bag-of-words":[44],"model.":[45],"The":[46],"segments":[47],"discovered":[48],"by":[49,98],"our":[50,99],"help":[52],"understand":[53],"this":[54,89],"underlying":[55],"grammatical":[56],"structure.":[57],"apply":[59],"statistical":[61],"model":[62],"based":[63],"on":[64],"Hoeffding's":[65],"Inequality":[66],"to":[67],"mine":[68],"significant":[69],"word":[70],"n-grams":[71],"subsequently":[75],"use":[76],"them":[77],"for":[78],"segmenting":[79],"Evaluation":[82],"against":[83],"manually":[84],"segmented":[85],"shows":[87],"technique":[90],"detect":[92],"rare":[93],"are":[96],"missed":[97],"Pointwise":[100],"Mutual":[101],"Information":[102],"(PMI)":[103],"baseline.":[104]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}