{"id":"https://openalex.org/W3210032674","doi":"https://doi.org/10.5220/0010710300003058","title":"Lbl2Vec: An Embedding-based Approach for Unsupervised Document Retrieval on Predefined Topics","display_name":"Lbl2Vec: An Embedding-based Approach for Unsupervised Document Retrieval on Predefined Topics","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3210032674","doi":"https://doi.org/10.5220/0010710300003058","mag":"3210032674"},"language":"en","primary_location":{"id":"doi:10.5220/0010710300003058","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010710300003058","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Web Information Systems and Technologies","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0010710300003058","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037301059","display_name":"Tim Schopf","orcid":"https://orcid.org/0000-0003-3849-0394"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Schopf","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Boltzmannstrasse 3, Garching, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Boltzmannstrasse 3, Garching, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036520551","display_name":"Daniel Braun","orcid":"https://orcid.org/0000-0001-8120-3368"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Braun","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Boltzmannstrasse 3, Garching, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Boltzmannstrasse 3, Garching, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022973212","display_name":"Florian Matthes","orcid":"https://orcid.org/0000-0002-6667-5452"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Matthes","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Boltzmannstrasse 3, Garching, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Boltzmannstrasse 3, Garching, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":3.0776,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93440789,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"124","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9987000226974487,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987000226974487,"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":0.9825999736785889,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9811000227928162,"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":0.8722646236419678},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.6480053663253784},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5786437392234802},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5777983069419861},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5302355289459229},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48610901832580566},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4821005165576935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4781007170677185},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4691903591156006},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.45896482467651367},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.42814862728118896},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3526381850242615},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3004035949707031},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10568255186080933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8722646236419678},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.6480053663253784},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5786437392234802},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5777983069419861},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5302355289459229},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48610901832580566},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4821005165576935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4781007170677185},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4691903591156006},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.45896482467651367},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.42814862728118896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3526381850242615},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3004035949707031},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10568255186080933},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5220/0010710300003058","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010710300003058","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Web Information Systems and Technologies","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/b63935f5-f5b3-46a1-b281-869e776c8cc1","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/b63935f5-f5b3-46a1-b281-869e776c8cc1","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Schopf, T, Braun, D & Matthes, F 2021, Lbl2Vec : An Embedding-based Approach for Unsupervised Document Retrieval on Predefined Topics. in Proceedings of the 17th International Conference on Web Information Systems and Technologies - WEBIST,. pp. 124-132. https://doi.org/10.5220/0010710300003058","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:2210.06023","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.06023","pdf_url":"https://arxiv.org/pdf/2210.06023","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:ut:oai:ris.utwente.nl:publications/b63935f5-f5b3-46a1-b281-869e776c8cc1","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/lbl2vec(b63935f5-f5b3-46a1-b281-869e776c8cc1).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 17th International Conference on Web Information Systems and Technologies - WEBIST,, 124 - 132","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"doi:10.5220/0010710300003058","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010710300003058","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Web Information Systems and Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2997627311","https://openalex.org/W2289741972","https://openalex.org/W4296501933","https://openalex.org/W3043161732","https://openalex.org/W4238415164","https://openalex.org/W2580878117","https://openalex.org/W3091147850","https://openalex.org/W2154282042","https://openalex.org/W2947963870","https://openalex.org/W2997152654"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,60,128,177,200],"consider":[4],"the":[5,34,74,88,92,134,161,167,191,202,213],"task":[6],"of":[7,31,50,141,197],"retrieving":[8,107,115],"documents":[9,82,109,116],"with":[10,110,172],"predefined":[11,119],"topics":[12,36,89,120],"from":[13,73,121,181,186],"an":[14,19,130,173],"unlabeled":[15,75],"document":[16,68,76,158],"dataset":[17,77,145,168],"using":[18],"unsupervised":[20,24,174],"approach.":[21],"The":[22,94],"proposed":[23,95],"approach":[25],"requires":[26,97],"only":[27],"a":[28,47,62,209],"small":[29],"number":[30],"keywords":[32],"describing":[33],"respective":[35,192],"and":[37,69,124,146,185],"no":[38,99],"labeled":[39],"document.":[40],"Existing":[41],"approaches":[42],"either":[43],"heavily":[44],"relied":[45],"on":[46,56,117,143,148,190],"large":[48],"amount":[49],"additionally":[51],"encoded":[52],"world":[53],"knowledge":[54],"or":[55],"term-document":[57],"frequencies.":[58],"Contrariwise,":[59],"introduce":[61],"method":[63,96,152],"that":[64,83],"learns":[65],"jointly":[66],"embedded":[67],"word":[70],"vectors":[71],"solely":[72],"in":[78,169],"order":[79],"to":[80,87,163,166,183,188],"find":[81],"are":[84],"semantically":[85],"similar":[86],"described":[90],"by":[91],"keywords.":[93],"almost":[98],"text":[100],"preprocessing":[101],"but":[102],"is":[103],"simultaneously":[104],"effective":[105],"at":[106],"relevant":[108],"high":[111],"probability.":[112],"When":[113],"successively":[114],"different":[118],"publicly":[122,206],"available":[123,207],"commonly":[125],"used":[126,155],"datasets,":[127],"achieved":[129],"average":[131],"area":[132],"under":[133,212],"receiver":[135],"operating":[136],"characteristic":[137],"curve":[138],"val":[139],"ue":[140],"0.95":[142],"one":[144],"0.92":[147],"another.":[149],"Further,":[150],"our":[151,198],"can":[153],"be":[154],"for":[156],"multiclass":[157],"classification,":[159],"without":[160],"need":[162],"assign":[164],"labels":[165],"advance.":[170],"Compared":[171],"classification":[175],"baseline,":[176],"increased":[178],"F1":[179],"scores":[180],"76.6":[182],"82.7":[184],"61.0":[187],"75.1":[189],"datasets.":[193],"For":[194],"easy":[195],"replication":[196],"approach,":[199],"make":[201],"developed":[203],"Lbl2Vec":[204],"code":[205],"as":[208],"ready-to-use":[210],"tool":[211],"3-Clause":[214],"BSD":[215],"license\u2217.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}