{"id":"https://openalex.org/W3005353706","doi":"https://doi.org/10.1145/3458553.3458567","title":"Search and analytics using semantic annotations","display_name":"Search and analytics using semantic annotations","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3005353706","doi":"https://doi.org/10.1145/3458553.3458567","mag":"3005353706"},"language":"en","primary_location":{"id":"doi:10.1145/3458553.3458567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458553.3458567","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGIR Forum","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://dx.doi.org/10.22028/D291-30078","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101456958","display_name":"Dhruv Gupta","orcid":"https://orcid.org/0009-0008-6364-482X"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dhruv Gupta","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101456958"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19331094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"53","issue":"2","first_page":"100","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9926000237464905,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9926000237464905,"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":0.9704999923706055,"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":0.9672999978065491,"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":0.9183861017227173},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7184572815895081},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.71268230676651},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5427402257919312},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5367879271507263},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5057306289672852},{"id":"https://openalex.org/keywords/phrase-search","display_name":"Phrase search","score":0.47538506984710693},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4625747501850128},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3184172511100769},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.2754438519477844},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.1804439127445221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9183861017227173},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7184572815895081},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.71268230676651},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5427402257919312},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5367879271507263},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5057306289672852},{"id":"https://openalex.org/C37202355","wikidata":"https://www.wikidata.org/wiki/Q7188071","display_name":"Phrase search","level":5,"score":0.47538506984710693},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4625747501850128},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3184172511100769},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2754438519477844},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.1804439127445221},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C14838553","wikidata":"https://www.wikidata.org/wiki/Q7441639","display_name":"Search analytics","level":4,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3458553.3458567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458553.3458567","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGIR Forum","raw_type":"journal-article"},{"id":"pmh:oai:publikationen.sulb.uni-saarland.de:20.500.11880/28516","is_oa":true,"landing_page_url":"http://dx.doi.org/10.22028/D291-30078","pdf_url":null,"source":{"id":"https://openalex.org/S4377196499","display_name":"Publications of the UdS (Saarland University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I91712215","host_organization_name":"Saarland University","host_organization_lineage":["https://openalex.org/I91712215"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:doctoralThesis"},{"id":"pmh:oai:pure.mpg.de:item_3186195","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0005-7695-E","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":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"pmh:oai:pure.mpg.de:item_3192600","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0005-A1C2-9","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":"ACM SIGIR Forum","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.22028/d291-30078","is_oa":true,"landing_page_url":"https://doi.org/10.22028/d291-30078","pdf_url":null,"source":{"id":"https://openalex.org/S7407052975","display_name":"Universit\u00e4t des Saarlandes","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:publikationen.sulb.uni-saarland.de:20.500.11880/28516","is_oa":true,"landing_page_url":"http://dx.doi.org/10.22028/D291-30078","pdf_url":null,"source":{"id":"https://openalex.org/S4377196499","display_name":"Publications of the UdS (Saarland University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I91712215","host_organization_name":"Saarland University","host_organization_lineage":["https://openalex.org/I91712215"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:doctoralThesis"},"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2800106761","https://openalex.org/W2919747665","https://openalex.org/W1981732427","https://openalex.org/W1984061923","https://openalex.org/W2129100979","https://openalex.org/W4313270463","https://openalex.org/W1975066779","https://openalex.org/W2092902419","https://openalex.org/W2039546652","https://openalex.org/W2343034896"],"abstract_inverted_index":{"Current":[0,131],"information":[1,15,110,232,432,466,485,738],"retrieval":[2,357],"systems":[3,133],"are":[4,134,245,555,594,647,661,706,732,794,805,819],"limited":[5],"to":[6,120,136,177,254,317,379,429,450,464,496,679,827,853,933,943,955,958],"text":[7,65,122,348,895,930,950],"in":[8,20,42,64,226,231,235,240,261,304,344,375,408,434,441,447,492,558,583,599,621,634,709,715,762,776,796,898,953,982],"documents":[9,125,717],"for":[10,74,162,168,269,300,393,511,536,719,756,873,916,929,977],"helping":[11,580],"users":[12,456,516],"with":[13,37,66,147,468],"their":[14,210,431,465,638,666,790,812,828],"needs.":[16,486],"With":[17],"the":[18,21,30,43,270,336,339,369,373,376,537,581,600,614,625,630,641,669,673,690,699,703,716,720,763,784,881,973],"progress":[19],"field":[22],"of":[23,32,45,78,96,309,313,361,372,410,444,529,544,569,602,632,637,676,736,765,780,824,834],"natural":[24],"language":[25],"processing,":[26],"there":[27],"now":[28],"exists":[29],"possibility":[31],"enriching":[33],"large":[34,79,97,192,262,417,458,493,585],"document":[35,82,100,194,263,418,459,494,512,519,586,730],"collections":[36,419,460,495,587,731],"accurate":[38],"semantic":[39,184,475,590,597,619,927],"annotations.":[40,185,476],"Annotations":[41],"form":[44,601,764],"part-of-speech":[46],"tags,":[47],"temporal":[48,484,490,509,563,567,603,642,766],"expressions,":[49,604,767],"numerical":[50],"values,":[51],"geographic":[52,605,768,813],"locations,":[53,606,701,769],"and":[54,76,94,114,183,201,209,238,319,363,384,387,414,461,549,566,574,607,645,658,702,741,770,799,839,860,896,931,948,979],"other":[55,608,771],"named":[56,323,327,609,773,817],"entities":[57,324,653,774,818,838],"can":[58,142,341,405,846,909],"help":[59,515,889],"us":[60],"look":[61],"at":[62,154,972],"terms":[63],"additional":[67],"semantics.":[68,639,791,858],"This":[69,438,938,964,985],"doctoral":[70,965],"dissertation":[71,966],"presents":[72],"methods":[73,472,915],"search":[75,132,167,189,892],"analysis":[77],"semantically":[80,98],"annotated":[81,99,193,729,894],"collections.":[83,101,264],"Concretely,":[84,366,611],"we":[85,156,196,221,354,367,404,470,481,488,521,577,612,746,841,862,884,913],"make":[86],"contributions":[87],"along":[88],"three":[89],"broad":[90],"directions:":[91],"indexing,":[92],"querying,":[93],"mining":[95],"Indexing":[102],"Annotated":[103,423,725],"Document":[104,424,726],"Collections.":[105,425,727],"Knowledge-centric":[106],"tasks":[107,560],"such":[108,138,561,654],"as":[109,140,531,562,650,652,655,711,713,807,821],"extraction,":[111,233],"question":[112,236],"answering,":[113,237],"relationship":[115,241],"extraction":[116],"require":[117],"a":[118,198,351,356,389,442,478,508,523,572,733,750,777,822,832],"user":[119,582],"retrieve":[121,406],"regions":[123,349,951],"within":[124,420,962],"that":[126,214,249,335,399,473,525,617,698,753,843,855,869,888],"detail":[127],"relationships":[128],"between":[129,180],"entities.":[130,328,610,742],"ill-equipped":[135],"handle":[137],"tasks,":[139],"they":[141],"only":[143],"provide":[144],"phrase":[145],"querying":[146],"Boolean":[148],"operators.":[149],"To":[150,186,329,346,454,514,879,902],"enable":[151],"knowledge":[152,256,411],"acquisition":[153],"scale,":[155],"propose":[157,355,388,471,522,613],"gyani,":[158],"an":[159,448,684,797,865],"indexing":[160,219],"infrastructure":[161,220],"knowledge-centric":[163,228],"tasks.":[164],"gyani":[165],"enables":[166],"structured":[169,871,891,956],"query":[170,268,378,395,445,532,538,564,721,886],"patterns":[171],"by":[172,215,588,682,759,787,969],"allowing":[173],"regular":[174],"expression":[175],"operators":[176,386,887],"be":[178,342,380,911],"expressed":[179],"word":[181,206],"sequences":[182],"implement":[187],"grep-like":[188],"capabilities":[190],"over":[191,811],"collections,":[195,520],"present":[197,748,775,863],"data":[199],"model":[200,368],"index":[202],"design":[203],"choices":[204],"involving":[205],"sequences,":[207],"annotations,":[208],"combinations.":[211],"We":[212,397],"show":[213,398,842],"using":[216,359,382,400,596,683,760,920],"our":[217,401,844],"proposed":[218,402],"bring":[222],"about":[223],"drastic":[224],"speedups":[225],"crucial":[227],"tasks:":[229],"95\u00d7":[230],"53\u00d7":[234],"12\u00d7":[239],"extraction.":[242],"Hyper-phrase":[243],"queries":[244,248,311,499,758,836,957],"multi-phrase":[246],"set":[247,779,823,833],"naturally":[250],"arise":[251],"when":[252,315,664,851],"attempting":[253,316],"spot":[255],"graph":[257,412],"facts":[258,413],"or":[259,325],"subgraphs":[260,415],"An":[265],"example":[266],"hyper-phrase":[267,310,352,377],"fact":[271,337],"\u2329mahatma":[272],"gandhi,":[273,282,285],"nominated":[274],"for,":[275],"nobel":[276,295,298,302],"peace":[277,296,305],"prize\u232a":[278],"is:":[279],"\u2329{":[280],"mahatma":[281],"m":[283],"k":[284],"gandhi":[286],"},":[287,293],"{":[288,294],"nominated,":[289],"nominee,":[290],"nomination":[291],"received":[292],"prize,":[297],"prize":[299,303],"peace,":[301],"}\u232a.":[306],"Efficient":[307],"execution":[308],"is":[312,333,941,987],"essence":[314],"verify":[318],"validate":[320],"claims":[321],"concerning":[322,338,739,837],"emerging":[326],"do":[330],"so,":[331],"it":[332],"required":[334],"entity":[340],"contextualized":[343],"text.":[345,878],"acquire":[347],"given":[350],"query,":[353],"framework":[358],"combinations":[360],"n-gram":[362],"skip-gram":[364],"indexes.":[365],"combinatorial":[370],"space":[371],"phrases":[374],"retrieved":[381,718,952],"vertical":[383],"horizontal":[385],"dynamic":[390],"programming":[391],"approach":[392,845],"optimized":[394],"processing.":[396],"optimizations":[403],"sentences":[407],"support":[409],"from":[416,876],"seconds.":[421,963],"Querying":[422],"Users":[426],"often":[427,439],"struggle":[428],"convey":[430],"needs":[433,467],"short":[435],"keyword":[436,757],"queries.":[437],"results":[440],"series":[443],"reformulations,":[446],"attempt":[449],"find":[451],"relevant":[452],"documents.":[453,570,781],"assist":[455],"navigate":[457],"lead":[462],"them":[463],"ease,":[469],"leverage":[474,489],"As":[477,571],"first":[479,626,747],"step,":[480,576,627],"focus":[482,578],"on":[483,579,893,926],"Specifically,":[487],"expressions":[491,643,793],"serve":[497],"time-sensitive":[498],"better.":[500],"Time-sensitive":[501],"queries,":[502],"e.g.,":[503],"summer":[504],"olympics":[505],"implicitly":[506],"carry":[507],"dimension":[510],"retrieval.":[513],"explore":[517],"longitudinal":[518],"method":[524],"generates":[526,618,870],"time":[527,542,553,704,801],"intervals":[528,543,554],"interest":[530,545],"reformulations.":[533],"For":[534,688,831],"instance,":[535,689],"world":[539],"war":[540],",":[541],"are:":[546],"[1914;":[547],"1918]":[548],"[1939;1945].":[550],"The":[551,592],"generated":[552,595],"immediately":[556],"useful":[557],"search-related":[559],"classification":[565],"diversification":[568],"second":[573],"final":[575],"navigating":[584],"generating":[589],"aspects.":[591],"aspects":[593,620],"annotations":[598,633,677,761],"xFactor":[615,628,670],"algorithm":[616,671],"two":[622],"steps.":[623],"In":[624,743],"computes":[629,672],"salience":[631,675],"models":[635,928],"informed":[636],"Thus,":[640],"1930s":[644],"1939":[646],"considered":[648,662],"similar":[649],"well":[651,712],"usain":[656],"bolt":[657],"justin":[659],"gatlin":[660],"related":[663],"computing":[665],"salience.":[667],"Second,":[668],"co-occurrence":[674],"belonging":[678],"different":[680],"types":[681],"efficient":[685],"partitioning":[686],"procedure.":[687],"aspect":[691],"\u2329{usain":[692],"bolt},":[693],"{beijing,":[694],"London},":[695],"[2008;2012]\u232a":[696],"signifies":[697],"entity,":[700],"interval":[705],"observed":[707],"frequently":[708],"isolation":[710],"together":[714,935,945],"olympic":[722],"medalists.":[723],"Mining":[724],"Large":[728],"treasure":[734],"trove":[735],"historical":[737],"events":[740,755],"this":[744],"regard,":[745],"EventMiner,":[749],"clustering":[751],"algorithm,":[752],"mines":[754],"disambiguated":[772,816],"pseudo-relevant":[778],"EventMiner":[782],"aggregates":[783],"annotation":[785,857],"evidences":[786],"mathematically":[788],"modeling":[789],"Temporal":[792],"modeled":[795,806,820],"uncertainty":[798],"proximity-aware":[800],"model.":[802],"Geographic":[803],"locations":[804],"minimum":[808],"bounding":[809],"rectangles":[810],"co-ordinates.":[814],"Other":[815],"links":[825],"corresponding":[826],"Wikipedia":[829],"articles.":[830],"history-oriented":[835],"events,":[840],"truly":[847],"identify":[848],"event":[849],"clusters":[850],"compared":[852],"approaches":[854],"disregard":[856],"Second":[859],"finally,":[861],"jigsaw,":[864],"end-to-end":[866],"query-driven":[867],"system":[868],"tables":[872,961],"user-defined":[874],"schema":[875],"unstructured":[877],"define":[880],"table":[882,899,904],"schema,":[883],"describe":[885,914],"perform":[890],"fill":[897],"cell":[900,905],"values.":[901],"resolve":[903],"values":[906,908,919],"whose":[907],"not":[910],"retrieved,":[912],"inferring":[917],"null":[918],"local":[921],"context.":[922],"jigsaw":[923,940],"further":[924],"relies":[925],"numbers":[932],"link":[934],"near-duplicate":[936],"rows.":[937],"way,":[939],"able":[942],"piece":[944],"paraphrased,":[946],"partial,":[947],"redundant":[949],"response":[954],"generate":[959],"high-quality":[960],"was":[967],"supervised":[968],"Klaus":[970],"Berberich":[971],"Max":[974],"Planck":[975],"Institute":[976],"Informatics":[978],"htw":[980],"saar":[981],"Saarbr\u00fccken,":[983],"Germany.":[984],"thesis":[986],"available":[988],"online":[989],"at:":[990],"https://people.mpi-inf.mpg.de/~dhgupta/pub/dhruv-thesis.pdf.":[991]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
