{"id":"https://openalex.org/W2911866459","doi":"https://doi.org/10.1109/bigdata.2018.8622647","title":"ANNOTATE: orgANizing uNstructured cOntenTs viA Topic labEls","display_name":"ANNOTATE: orgANizing uNstructured cOntenTs viA Topic labEls","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2911866459","doi":"https://doi.org/10.1109/bigdata.2018.8622647","mag":"2911866459"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10197/9888","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068434278","display_name":"Deepak Ajwani","orcid":"https://orcid.org/0000-0001-7269-4150"},"institutions":[{"id":"https://openalex.org/I4210105201","display_name":"Nokia (Ireland)","ror":"https://ror.org/01dcaj468","country_code":"IE","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210105201"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Deepak Ajwani","raw_affiliation_strings":["Nokia Bell Labs, Ireland"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Ireland","institution_ids":["https://openalex.org/I4210105201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027835501","display_name":"Bilyana Taneva","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105201","display_name":"Nokia (Ireland)","ror":"https://ror.org/01dcaj468","country_code":"IE","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210105201"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Bilyana Taneva","raw_affiliation_strings":["Nokia Bell Labs, Ireland"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Ireland","institution_ids":["https://openalex.org/I4210105201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053023517","display_name":"Sourav Dutta","orcid":"https://orcid.org/0000-0002-8934-9166"},"institutions":[{"id":"https://openalex.org/I4210105201","display_name":"Nokia (Ireland)","ror":"https://ror.org/01dcaj468","country_code":"IE","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210105201"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Sourav Dutta","raw_affiliation_strings":["Nokia Bell Labs, Ireland"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Ireland","institution_ids":["https://openalex.org/I4210105201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023616249","display_name":"Patrick K. Nicholson","orcid":"https://orcid.org/0000-0001-5867-5973"},"institutions":[{"id":"https://openalex.org/I4210105201","display_name":"Nokia (Ireland)","ror":"https://ror.org/01dcaj468","country_code":"IE","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210105201"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Patrick K. Nicholson","raw_affiliation_strings":["Nokia Bell Labs, Ireland"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Ireland","institution_ids":["https://openalex.org/I4210105201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054532111","display_name":"Ghasem Heyrani-Nobari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105201","display_name":"Nokia (Ireland)","ror":"https://ror.org/01dcaj468","country_code":"IE","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210105201"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Ghasem Heyrani-Nobari","raw_affiliation_strings":["Nokia Bell Labs, Ireland"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Ireland","institution_ids":["https://openalex.org/I4210105201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029966654","display_name":"Alessandra Sala","orcid":"https://orcid.org/0000-0003-2966-1518"},"institutions":[{"id":"https://openalex.org/I4210105201","display_name":"Nokia (Ireland)","ror":"https://ror.org/01dcaj468","country_code":"IE","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210105201"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Alessandra Sala","raw_affiliation_strings":["Nokia Bell Labs, Ireland"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Ireland","institution_ids":["https://openalex.org/I4210105201"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5068434278"],"corresponding_institution_ids":["https://openalex.org/I4210105201"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17218938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1699","last_page":"1708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9969000220298767,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8483437299728394},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6625580787658691},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5818755626678467},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5423794984817505},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.5223280787467957},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4616478979587555},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4394015371799469},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.43256473541259766},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.3992964029312134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36969324946403503},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3425118327140808},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24918773770332336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483437299728394},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6625580787658691},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5818755626678467},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5423794984817505},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.5223280787467957},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4616478979587555},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4394015371799469},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.43256473541259766},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3992964029312134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36969324946403503},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3425118327140808},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24918773770332336},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2018.8622647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:researchrepository.ucd.ie:10197/9888","is_oa":true,"landing_page_url":"http://hdl.handle.net/10197/9888","pdf_url":"http://hdl.handle.net/10197/9888","source":{"id":"https://openalex.org/S4306402280","display_name":"Research Repository UCD (University College Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I100930933","host_organization_name":"University College Dublin","host_organization_lineage":["https://openalex.org/I100930933"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Publication"}],"best_oa_location":{"id":"pmh:oai:researchrepository.ucd.ie:10197/9888","is_oa":true,"landing_page_url":"http://hdl.handle.net/10197/9888","pdf_url":"http://hdl.handle.net/10197/9888","source":{"id":"https://openalex.org/S4306402280","display_name":"Research Repository UCD (University College Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I100930933","host_organization_name":"University College Dublin","host_organization_lineage":["https://openalex.org/I100930933"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Publication"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2911866459.pdf"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W55768394","https://openalex.org/W99317934","https://openalex.org/W152260871","https://openalex.org/W177984263","https://openalex.org/W1546425806","https://openalex.org/W1612003148","https://openalex.org/W1880262756","https://openalex.org/W1965893683","https://openalex.org/W1967542092","https://openalex.org/W1971937094","https://openalex.org/W1975719446","https://openalex.org/W1980885411","https://openalex.org/W1987874268","https://openalex.org/W2013579020","https://openalex.org/W2022166150","https://openalex.org/W2025844353","https://openalex.org/W2026601878","https://openalex.org/W2027869746","https://openalex.org/W2063862666","https://openalex.org/W2065251533","https://openalex.org/W2065843886","https://openalex.org/W2067472918","https://openalex.org/W2067802667","https://openalex.org/W2091047798","https://openalex.org/W2097807612","https://openalex.org/W2113499583","https://openalex.org/W2113855231","https://openalex.org/W2117805756","https://openalex.org/W2120391124","https://openalex.org/W2123142779","https://openalex.org/W2127723919","https://openalex.org/W2129250947","https://openalex.org/W2133517430","https://openalex.org/W2135140174","https://openalex.org/W2145049651","https://openalex.org/W2146241755","https://openalex.org/W2153225416","https://openalex.org/W2154897810","https://openalex.org/W2171785178","https://openalex.org/W2250355330","https://openalex.org/W2420602380","https://openalex.org/W2619910338","https://openalex.org/W2736177616","https://openalex.org/W2798965707","https://openalex.org/W2950225692","https://openalex.org/W4231510805","https://openalex.org/W6606173638","https://openalex.org/W6607321472","https://openalex.org/W6632714361","https://openalex.org/W6636440780","https://openalex.org/W6639619044","https://openalex.org/W6656957402","https://openalex.org/W6677063751","https://openalex.org/W6677712588","https://openalex.org/W6677732584","https://openalex.org/W6679196975","https://openalex.org/W6680273311","https://openalex.org/W6717099040","https://openalex.org/W7034766929"],"related_works":["https://openalex.org/W2136735429","https://openalex.org/W3157828377","https://openalex.org/W4377992839","https://openalex.org/W244044452","https://openalex.org/W2937168573","https://openalex.org/W2261525379","https://openalex.org/W2805468299","https://openalex.org/W4231652189","https://openalex.org/W2889935511","https://openalex.org/W2608358066"],"abstract_inverted_index":{"With":[0],"the":[1,27,56,79,88,94,97,152,158,181],"advent":[2],"of":[3,11,42,51,90,103,120,125,132,165,190,214],"Big":[4],"Data":[5],"paradigm,":[6],"filtering,":[7],"retrieval,":[8],"and":[9,29,70,106,122,187,223,227],"linking":[10,228],"unstructured":[12,38],"multi-modal":[13],"data":[14,84],"has":[15],"become":[16],"a":[17,33,111,117,129,162],"necessity.":[18],"Assigning":[19],"topic":[20,92],"labels":[21,147],"to":[22,86,99,127,172,203],"contents,":[23],"that":[24,142],"accurately":[25],"capture":[26],"meaning":[28],"contextual":[30],"information,":[31],"is":[32],"fundamental":[34],"problem":[35],"in":[36],"organizing":[37],"data.":[39,138],"The":[40],"usage":[41],"manually-assigned":[43],"tags":[44,174],"for":[45,148,154,175,184,218],"this":[46],"purpose":[47],"introduces":[48],"inconsistencies":[49],"because":[50],"different":[52],"\"surface":[53],"forms\".":[54],"On":[55],"other":[57],"hand,":[58],"existing":[59],"automated":[60],"approaches":[61],"either":[62],"use":[63],"hierarchical":[64],"multi-label":[65],"classification,":[66],"or":[67],"are":[68,107],"unsupervised":[69],"rely":[71],"on":[72,116,161,180,195],"(undirected)":[73],"graph":[74],"measures":[75],"leveraging":[76],"taxonomies.":[77],"While":[78],"former":[80],"requires":[81],"large":[82],"training":[83,137],"set":[85,119,164],"learn":[87,100,128],"characteristics":[89],"each":[91],"class,":[93],"latter":[95],"lacks":[96],"flexibility":[98],"broad":[101,130],"range":[102],"related":[104,133,229],"topics":[105,134],"less":[108],"accurate.We":[109],"propose":[110],"novel":[112],"framework,":[113,159],"ANNOTATE":[114],"based":[115,194],"small":[118,163],"features":[121],"directed":[123],"traversal":[124],"taxonomies":[126],"spectrum":[131],"using":[135],"limited":[136],"We":[139],"also":[140],"show":[141,200],"our":[143,201,215,233],"approach":[144,202],"provides":[145],"accurate":[146],"several":[149],"domains":[150],"without":[151],"need":[153],"re-training.":[155],"For":[156],"instance,":[157],"trained":[160],"BBC":[166],"news":[167,185],"articles,":[168],"exhibits":[169],"close":[170],"matches":[171],"user-generated":[173],"Quora":[176,221],"documents.":[177],"Experimental":[178],"results,":[179],"same":[182],"model,":[183],"classification":[186],"identifying":[188],"aspects":[189],"Amazon":[191,196],"product":[192],"reviews,":[193],"Mechanical":[197],"Turk":[198],"evaluation":[199],"be":[204],"significantly":[205],"better":[206],"than":[207],"state-of-the-art.We":[208],"further":[209],"present":[210],"real-life":[211],"case":[212],"studies":[213],"proposed":[216],"framework":[217],"automatically":[219],"tagging":[220],"posts,":[222],"topically":[224],"segmenting,":[225],"indexing":[226],"YouTube":[230],"videos":[231],"(using":[232],"publicly":[234],"available":[235],"Chrome":[236],"browser":[237],"extension).":[238]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}