{"id":"https://openalex.org/W2070117792","doi":"https://doi.org/10.1109/bigdata.2014.7004314","title":"Query revision during cluster based search on large unstructured corpora","display_name":"Query revision during cluster based search on large unstructured corpora","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2070117792","doi":"https://doi.org/10.1109/bigdata.2014.7004314","mag":"2070117792"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","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/A5077747661","display_name":"Vinay Deolalikar","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vinay Deolalikar","raw_affiliation_strings":["Hewlett-Packard Research, Sunnyvale, CA","Hewlett-Packard Research, Sunnyvale, CA 94089"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Research, Sunnyvale, CA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Research, Sunnyvale, CA 94089","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077747661"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09595098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2997","issue":null,"first_page":"845","last_page":"853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9965999722480774,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9965999722480774,"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":0.9965000152587891,"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":0.9943000078201294,"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":0.7781358957290649},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5598266124725342},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.500157356262207},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.42765581607818604},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12540271878242493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7781358957290649},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5598266124725342},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.500157356262207},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.42765581607818604},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12540271878242493}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2014.7004314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W19293941","https://openalex.org/W129655323","https://openalex.org/W146156986","https://openalex.org/W1517703053","https://openalex.org/W1522930108","https://openalex.org/W1528262008","https://openalex.org/W1532325895","https://openalex.org/W1577798322","https://openalex.org/W1605510967","https://openalex.org/W1651093245","https://openalex.org/W1956559956","https://openalex.org/W1963658069","https://openalex.org/W1996764654","https://openalex.org/W2000569744","https://openalex.org/W2003650253","https://openalex.org/W2027445772","https://openalex.org/W2038324731","https://openalex.org/W2041565863","https://openalex.org/W2043102839","https://openalex.org/W2045584315","https://openalex.org/W2061198046","https://openalex.org/W2065938637","https://openalex.org/W2074449313","https://openalex.org/W2079168273","https://openalex.org/W2079370602","https://openalex.org/W2080744761","https://openalex.org/W2086298942","https://openalex.org/W2087408015","https://openalex.org/W2100260099","https://openalex.org/W2114804204","https://openalex.org/W2129632406","https://openalex.org/W2130900715","https://openalex.org/W2137819016","https://openalex.org/W2145036943","https://openalex.org/W2145674033","https://openalex.org/W2150240006","https://openalex.org/W2155194165","https://openalex.org/W2155238363","https://openalex.org/W2155482025","https://openalex.org/W2155961949","https://openalex.org/W2325227998","https://openalex.org/W2413512986","https://openalex.org/W2504511805","https://openalex.org/W2964213887","https://openalex.org/W4213009331","https://openalex.org/W4231917132","https://openalex.org/W4234200495","https://openalex.org/W4237623536","https://openalex.org/W4241122026","https://openalex.org/W4244975643","https://openalex.org/W4252076394","https://openalex.org/W4285719527","https://openalex.org/W6605837613","https://openalex.org/W6631307971","https://openalex.org/W6634560786","https://openalex.org/W6636528456","https://openalex.org/W6637231022","https://openalex.org/W6650218246","https://openalex.org/W6724970696","https://openalex.org/W6766130689"],"related_works":["https://openalex.org/W3001245047","https://openalex.org/W1873153460","https://openalex.org/W850316024","https://openalex.org/W2170059263","https://openalex.org/W2044231962","https://openalex.org/W2945915803","https://openalex.org/W2969770061","https://openalex.org/W301348785","https://openalex.org/W2117230983","https://openalex.org/W4390861283"],"abstract_inverted_index":{"We":[0,173],"investigate":[1],"a":[2,40,139,175,196,201,204,221,242,265],"frequently":[3],"occurring":[4],"issue":[5],"in":[6,9,23,87,164,276],"search":[7,168,274],"(retrieval)":[8],"the":[10,82,88,93,102,109,113,117,130,155,159,181,211,215,219,224,246,254,257,304],"age":[11],"of":[12,37,47,61,65,84,90,158,183,190,203,223,256,264,296,307],"big":[13],"unstructured":[14,20,171],"data.":[15],"Searches":[16],"conducted":[17],"on":[18],"large":[19,170],"corpora":[21],"result":[22],"long":[24,49,205,225],"results":[25,28,137],"lists.":[26],"Such":[27],"lists":[29,119,297],"are":[30,99,106],"often":[31],"clustered":[32],"and":[33,111,128,142,149,237,268],"reranked":[34,52,207],"for":[35,120,233],"ease":[36],"navigation.":[38],"Should":[39],"query":[41,94,110,122,231,269,283],"be":[42,125,133,147],"revised":[43],"during":[44,58,303],"time-critical":[45],"examinations":[46],"such":[48,67,311],"cluster":[50],"based":[51],"lists?":[53],"This":[54,209,217,248],"question":[55,86],"arises":[56],"naturally":[57],"early":[59,305],"stages":[60,306],"commercially":[62,308],"important":[63,309],"applications":[64,166,310],"IR":[66],"as":[68,241,287,289,312],"eDiscovery,":[69],"but":[70],"has":[71],"not":[72],"yet":[73],"been":[74],"given":[75],"any":[76],"research":[77],"attention.":[78],"Four":[79],"factors":[80],"compound":[81],"difficulty":[83],"this":[85,234],"setting":[89],"eDiscovery:":[91],"(a)":[92],"sources":[95],"(the":[96],"technical":[97],"experts)":[98],"different":[100],"from":[101],"legal":[103],"staff":[104,275],"that":[105],"actually":[107],"executing":[108],"using":[112],"retrieval":[114],"system,":[115],"(b)":[116],"retrieved":[118,136],"each":[121],"tend":[123],"to":[124,151,154,177,185,214,245,252,279],"very":[126,299],"long,":[127],"(c)":[129,143],"user":[131,220],"might":[132],"accessing":[134],"these":[135],"through":[138],"clustering":[140],"interface,":[141],"all":[144],"decisions":[145],"must":[146],"transparent":[148],"easy":[150],"explain":[152],"due":[153],"litigious":[156],"nature":[157],"application.":[160],"Analogous":[161],"difficulties":[162],"arise":[163],"other":[165],"involving":[167],"over":[169],"corpora.":[172],"introduce":[174,195],"framework":[176,188],"help":[178],"users":[179],"make":[180],"decision":[182],"\u201cwhether":[184],"revise.\u201d":[186],"Our":[187],"consists":[189],"two":[191],"components.":[192],"First,":[193],"we":[194,229],"\u201climited":[197],"view\u201d":[198],"which":[199],"is":[200,210,250],"summary":[202,222,258],"cluster-based":[206,226],"list.":[208,227],"first":[212],"input":[213,244],"user.":[216,247],"provides":[218],"Second,":[228],"construct":[230],"predictors":[232],"limited":[235,259,266],"view,":[236],"provide":[238],"their":[239],"prediction":[240,249,271],"second":[243],"used":[251],"corroborate":[253],"inspection":[255],"view.":[260],"The":[261],"proposed":[262],"combination":[263],"view":[267],"performance":[270],"can":[272],"assist":[273],"determining":[277],"whether":[278],"pursue":[280],"an":[281],"expensive":[282],"revision":[284],"or":[285],"not,":[286],"well":[288],"save":[290],"precious":[291],"time":[292],"by":[293],"precluding":[294],"inspections":[295],"with":[298],"few":[300],"relevant":[301],"documents":[302],"eDiscovery.":[313]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}