{"id":"https://openalex.org/W2089818016","doi":"https://doi.org/10.1145/2247596.2247628","title":"Top-k interesting phrase mining in ad-hoc collections using sequence pattern indexing","display_name":"Top-k interesting phrase mining in ad-hoc collections using sequence pattern indexing","publication_year":2012,"publication_date":"2012-03-27","ids":{"openalex":"https://openalex.org/W2089818016","doi":"https://doi.org/10.1145/2247596.2247628","mag":"2089818016"},"language":"en","primary_location":{"id":"doi:10.1145/2247596.2247628","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","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/A5053771245","display_name":"Chuancong Gao","orcid":"https://orcid.org/0000-0003-1724-5947"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chuancong Gao","raw_affiliation_strings":["Saarland University, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043223305","display_name":"Sebastian Michel","orcid":"https://orcid.org/0000-0001-6636-2694"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Michel","raw_affiliation_strings":["Saarland University, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":1.4592,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.87961448,"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":"264","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9984999895095825,"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/T11106","display_name":"Data Management and Algorithms","score":0.9966999888420105,"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":0.8640084266662598},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7409056425094604},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6000936031341553},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5257024765014648},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.49917030334472656},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.44910499453544617},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4468228220939636},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.41064688563346863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3438340723514557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8640084266662598},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7409056425094604},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6000936031341553},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5257024765014648},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.49917030334472656},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.44910499453544617},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4468228220939636},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.41064688563346863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3438340723514557},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2247596.2247628","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.233.2073","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.233.2073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.edbt.org/Proceedings/2012-Berlin/papers/edbt/a30-gao.pdf","raw_type":"text"},{"id":"pmh:oai:pure.mpg.de:item_1837057","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0014-575D-4","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advances in Database Technology - EDBT 2012","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1584003909","https://openalex.org/W1856092728","https://openalex.org/W2026302857","https://openalex.org/W2049859567","https://openalex.org/W2053606794","https://openalex.org/W2111254498","https://openalex.org/W2111593814","https://openalex.org/W2116396873","https://openalex.org/W2117169652","https://openalex.org/W2123061032","https://openalex.org/W2126940099","https://openalex.org/W2132219058","https://openalex.org/W2144212226","https://openalex.org/W2147694185","https://openalex.org/W2154553070","https://openalex.org/W2154642793","https://openalex.org/W2154921200","https://openalex.org/W2158454296","https://openalex.org/W2166559705","https://openalex.org/W6681242987"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W4234886518","https://openalex.org/W2130160813","https://openalex.org/W2389591058","https://openalex.org/W2054476758"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,199],"consider":[4],"the":[5,24,47,49,66,72,87,106,152,156,172,193,202],"problem":[6],"of":[7,39,43,46,51,68,93,144,162],"mining":[8,135,158,196],"frequently":[9],"occurring":[10],"interesting":[11,90],"phrases":[12,91,109,120],"in":[13,17,201],"large":[14],"document":[15,54],"collections":[16,55],"an":[18,36,122],"ad-hoc":[19,53],"fashion.":[20],"Ad-hoc":[21],"refers":[22],"to":[23,26,85],"ability":[25],"perform":[27],"such":[28],"analyses":[29],"over":[30],"text":[31],"corpora":[32],"that":[33,103,108,170],"can":[34],"be":[35],"arbitrary":[37],"subset":[38],"a":[40,59,75,94,115,142,145,181,189],"global":[41],"set":[42],"documents.":[44],"Most":[45],"times":[48],"identification":[50],"these":[52,139],"is":[56,141],"driven":[57],"by":[58,151],"user":[60],"or":[61],"application":[62],"defined":[63],"query":[64],"with":[65,126],"aim":[67],"gathering":[69],"statistics":[70],"describing":[71],"sub-collection,":[73],"as":[74,186,188,198],"starting":[76],"point":[77],"for":[78,119,192],"further":[79,123],"data":[80,157],"analysis":[81],"tasks.":[82],"Our":[83],"approach":[84,177],"mine":[86],"top-k":[88,133,194],"most":[89],"consists":[92],"novel":[95],"indexing":[96],"technique,":[97],"called":[98],"Sequence":[99],"Pattern":[100],"Indexing":[101],"(SeqPattIndex),":[102],"benefits":[104],"from":[105,155],"observation":[107],"often":[110],"overlap":[111],"sequentially.":[112],"We":[113],"devise":[114],"forest":[116],"based":[117],"index":[118,183],"and":[121,149,165],"improved":[124],"version":[125],"additional":[127],"redundancy":[128],"elimination":[129],"power.":[130],"The":[131],"actual":[132],"phrase":[134,195],"algorithm":[136],"operating":[137],"on":[138,179],"indices":[140],"combination":[143],"simple":[146],"merge":[147],"join":[148],"inspired":[150],"pattern-growth":[153],"framework":[154],"community,":[159],"making":[160],"use":[161],"early":[163],"termination":[164],"search":[166],"space":[167,184],"pruning":[168],"technologies":[169],"enhance":[171],"runtime":[173,191],"performance.":[174],"Overall,":[175],"our":[176],"has":[178],"average":[180],"lower":[182,190],"consumption":[185],"well":[187],"task,":[197],"demonstrate":[200],"experimental":[203],"evaluation":[204],"using":[205],"real-world":[206],"data.":[207]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}