{"id":"https://openalex.org/W3011493836","doi":"https://doi.org/10.14778/3380750.3380754","title":"Effective and efficient retrieval of structured entities","display_name":"Effective and efficient retrieval of structured entities","publication_year":2020,"publication_date":"2020-02-01","ids":{"openalex":"https://openalex.org/W3011493836","doi":"https://doi.org/10.14778/3380750.3380754","mag":"3011493836"},"language":"en","primary_location":{"id":"doi:10.14778/3380750.3380754","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3380750.3380754","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5101688217","display_name":"Ruihong Huang","orcid":"https://orcid.org/0000-0002-4572-4243"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruihong Huang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084430029","display_name":"Shaoxu Song","orcid":"https://orcid.org/0000-0002-9503-2755"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxu Song","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102887835","display_name":"Yunsu Lee","orcid":"https://orcid.org/0000-0001-9413-7734"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunsu Lee","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611466","display_name":"Jung\u2010Ho Park","orcid":"https://orcid.org/0000-0002-6708-6692"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungho Park","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100605822","display_name":"Soo-Hyung Kim","orcid":"https://orcid.org/0000-0003-3575-5035"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soo-Hyung Kim","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044526668","display_name":"Sungmin Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungmin Yi","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101688217"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.7181,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73596507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"13","issue":"6","first_page":"826","last_page":"839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8324481248855591},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6989791989326477},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.5213167071342468},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.49067580699920654},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46761688590049744},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45753294229507446},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4307374954223633},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.42639458179473877},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4219588339328766},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.255642831325531},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.23002654314041138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17973211407661438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324481248855591},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6989791989326477},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.5213167071342468},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.49067580699920654},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46761688590049744},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45753294229507446},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4307374954223633},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.42639458179473877},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4219588339328766},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.255642831325531},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.23002654314041138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17973211407661438},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3380750.3380754","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3380750.3380754","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W8870360","https://openalex.org/W54366487","https://openalex.org/W100919058","https://openalex.org/W1539585011","https://openalex.org/W1560851690","https://openalex.org/W1600556920","https://openalex.org/W1614298861","https://openalex.org/W1628571627","https://openalex.org/W1956559956","https://openalex.org/W1982350890","https://openalex.org/W1989944922","https://openalex.org/W1991897642","https://openalex.org/W2000300218","https://openalex.org/W2008742021","https://openalex.org/W2010916971","https://openalex.org/W2019876129","https://openalex.org/W2019914167","https://openalex.org/W2019971182","https://openalex.org/W2038281398","https://openalex.org/W2049534074","https://openalex.org/W2049870103","https://openalex.org/W2065290081","https://openalex.org/W2077911025","https://openalex.org/W2078396654","https://openalex.org/W2081580037","https://openalex.org/W2084988263","https://openalex.org/W2090040833","https://openalex.org/W2096742765","https://openalex.org/W2099021858","https://openalex.org/W2105484782","https://openalex.org/W2117461391","https://openalex.org/W2127672769","https://openalex.org/W2134206624","https://openalex.org/W2148019918","https://openalex.org/W2155157903","https://openalex.org/W2156298111","https://openalex.org/W2156580346","https://openalex.org/W2165515835","https://openalex.org/W2250539671","https://openalex.org/W2250998089","https://openalex.org/W2583231427","https://openalex.org/W4256424005","https://openalex.org/W6600367688","https://openalex.org/W6602213441"],"related_works":["https://openalex.org/W2953408675","https://openalex.org/W2907632052","https://openalex.org/W2783390439","https://openalex.org/W137909637","https://openalex.org/W1600764354","https://openalex.org/W1549289070","https://openalex.org/W1788528807","https://openalex.org/W1813356921","https://openalex.org/W2562899248","https://openalex.org/W1536727034"],"abstract_inverted_index":{"Structured":[0],"entities":[1,18,34,55,114],"are":[2,151],"commonly":[3],"abstracted,":[4],"such":[5],"as":[6],"from":[7,56],"XML,":[8],"RDF":[9],"or":[10,117,166],"hidden-web":[11],"databases.":[12],"Direct":[13],"retrieval":[14,74,111],"of":[15,88,100,112,138],"various":[16,66],"structured":[17,45,105,140,191],"is":[19,128,202],"highly":[20],"demanded":[21],"in":[22,135,157,185],"data":[23],"lakes,":[24],"e.g.,":[25],"given":[26],"a":[27,123,139],"JSON":[28],"object,":[29],"to":[30,65,79,130,153],"find":[31],"the":[32,37,51,73,86,89,97,110,121,132,144,155,159,164,170,177],"XML":[33],"that":[35,72,199],"denote":[36],"same":[38,145],"real-world":[39],"object.":[40],"Existing":[41],"approaches":[42],"on":[43,85,195],"evaluating":[44],"entity":[46,149],"similarity":[47],"emphasize":[48],"too":[49],"much":[50],"structural":[52,80],"inconsistency.":[53],"Indeed,":[54],"heterogeneous":[57],"sources":[58],"could":[59,75,173],"have":[60],"very":[61],"distinct":[62],"structures,":[63],"owing":[64],"information":[67],"representation":[68],"conventions.":[69],"We":[70],"argue":[71],"be":[76],"more":[77,84],"tolerant":[78],"differences":[81],"and":[82,161,180,204],"focus":[83],"contents":[87],"entities.":[90,168,192],"In":[91],"this":[92],"paper,":[93],"we":[94],"first":[95],"identify":[96],"unique":[98],"challenge":[99],"parent-child":[101],"(containment)":[102],"relationships":[103],"among":[104],"entities,":[106],"which":[107],"unfortunately":[108],"prevent":[109],"proper":[113],"(returning":[115],"parents":[116],"children).":[118],"To":[119],"solve":[120],"problem,":[122],"novel":[124],"hierarchy":[125],"smooth":[126],"function":[127],"proposed":[129,171],"combine":[131],"term":[133],"scores":[134],"different":[136],"nodes":[137],"entity.":[141],"Entities":[142],"sharing":[143],"structure,":[146],"namely":[147],"an":[148],"family,":[150],"employed":[152],"learn":[154],"coefficient":[156],"aggregating":[158],"scores,":[160],"thus":[162],"distinguish/prune":[163],"parent":[165],"child":[167],"Remarkably,":[169],"method":[172],"cooperate":[174],"with":[175],"both":[176],"bag-of-words":[178],"(BOW)":[179],"word":[181],"embedding":[182],"models,":[183],"successful":[184],"retrieving":[186],"unstructured":[187],"documents,":[188],"for":[189],"querying":[190],"Extensive":[193],"experiments":[194],"real":[196],"datasets":[197],"demonstrate":[198],"our":[200],"proposal":[201],"effective":[203],"efficient.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}