{"id":"https://openalex.org/W4388894022","doi":"https://doi.org/10.1109/iceccs59891.2023.00015","title":"How to select samples for active learning? Document clustering with active learning methodology","display_name":"How to select samples for active learning? Document clustering with active learning methodology","publication_year":2023,"publication_date":"2023-06-14","ids":{"openalex":"https://openalex.org/W4388894022","doi":"https://doi.org/10.1109/iceccs59891.2023.00015"},"language":"en","primary_location":{"id":"doi:10.1109/iceccs59891.2023.00015","doi":"https://doi.org/10.1109/iceccs59891.2023.00015","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceccs59891.2023.00015","pdf_url":null,"source":{"id":"https://openalex.org/S7407088032","display_name":"IEEE International Conference on Engineering of Complex Computer Systems (ICECCS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 27th International Conference on Engineering of Complex Computer Systems (ICECCS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5038963939","display_name":"Norbert Ropiak","orcid":"https://orcid.org/0000-0003-3616-1298","observed_orcids":["https://orcid.org/0000-0003-3616-1298"]},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Norbert Ropiak","raw_affiliation_strings":["Wroc\u0142aw University of Science and Technology,CLARIN-PL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wroc\u0142aw University of Science and Technology,CLARIN-PL","institution_ids":["https://openalex.org/I11923345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102772341","display_name":"Mateusz Gniewkowski","orcid":"https://orcid.org/0000-0002-0620-8123","observed_orcids":["https://orcid.org/0000-0002-0620-8123"]},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Mateusz Gniewkowski","raw_affiliation_strings":["Wroc\u0142aw University of Science and Technology,CLARIN-PL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wroc\u0142aw University of Science and Technology,CLARIN-PL","institution_ids":["https://openalex.org/I11923345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091050693","display_name":"Micha\u0142 Sw\u0119drowski","orcid":"https://orcid.org/0000-0001-8029-6582","observed_orcids":["https://orcid.org/0000-0001-8029-6582"]},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Michal Swedrowski","raw_affiliation_strings":["Wroc\u0142aw University of Science and Technology,CLARIN-PL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wroc\u0142aw University of Science and Technology,CLARIN-PL","institution_ids":["https://openalex.org/I11923345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013801182","display_name":"Micha\u0142 Pogoda","orcid":"https://orcid.org/0000-0002-5011-5573","observed_orcids":["https://orcid.org/0000-0002-5011-5573"]},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Michal Pogoda","raw_affiliation_strings":["Wroc\u0142aw University of Science and Technology,CLARIN-PL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wroc\u0142aw University of Science and Technology,CLARIN-PL","institution_ids":["https://openalex.org/I11923345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073109972","display_name":"Karol Gawron","orcid":"https://orcid.org/0000-0002-1020-3018","observed_orcids":["https://orcid.org/0000-0002-1020-3018"]},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Karol Gawron","raw_affiliation_strings":["Wroc\u0142aw University of Science and Technology,CLARIN-PL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wroc\u0142aw University of Science and Technology,CLARIN-PL","institution_ids":["https://openalex.org/I11923345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031891503","display_name":"Bart\u0142omiej Bojanowski","orcid":"https://orcid.org/0000-0002-4879-8854","observed_orcids":["https://orcid.org/0000-0002-4879-8854"]},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Bartlomiej Bojanowski","raw_affiliation_strings":["Wroc\u0142aw University of Science and Technology,CLARIN-PL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wroc\u0142aw University of Science and Technology,CLARIN-PL","institution_ids":["https://openalex.org/I11923345"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010635837","display_name":"Tomasz Walkowiak","orcid":"https://orcid.org/0000-0002-7749-4251","observed_orcids":["https://orcid.org/0000-0002-7749-4251","https://orcid.org/0000-0003-1452-3067"]},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Tomasz Walkowiak","raw_affiliation_strings":["Wroc\u0142aw University of Science and Technology,CLARIN-PL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wroc\u0142aw University of Science and Technology,CLARIN-PL","institution_ids":["https://openalex.org/I11923345"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I11923345"],"apc_list":null,"apc_paid":null,"fwci":0.1105,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.26502952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"32","issue":null,"first_page":"42","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9390000104904175,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9390000104904175,"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":0.016300000250339508,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.011599999852478504,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.9990000128746033},{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.7639999985694885},{"id":"https://openalex.org/keywords/topic-modeling","display_name":"topic modeling","score":0.8299999833106995},{"id":"https://openalex.org/keywords/text-similarity","display_name":"text similarity","score":0.7940000295639038},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.8069999814033508},{"id":"https://openalex.org/keywords/annotation-cost-reduction","display_name":"annotation cost reduction","score":0.5379999876022339}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.78572678565979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850000262260437},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5928622484207153},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5752988457679749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5747619271278381},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.553869366645813},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5482601523399353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4740975797176361},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.45020973682403564},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4431791305541992},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43926364183425903},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.41894179582595825},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08070370554924011},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceccs59891.2023.00015","doi":"https://doi.org/10.1109/iceccs59891.2023.00015","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceccs59891.2023.00015","pdf_url":null,"source":{"id":"https://openalex.org/S7407088032","display_name":"IEEE International Conference on Engineering of Complex Computer Systems (ICECCS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 27th International Conference on Engineering of Complex Computer Systems (ICECCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1978633512","https://openalex.org/W2101234009","https://openalex.org/W2127218421","https://openalex.org/W2138621090","https://openalex.org/W2170240176","https://openalex.org/W2299467264","https://openalex.org/W2612690371","https://openalex.org/W2618851150","https://openalex.org/W2896457183","https://openalex.org/W2950813464","https://openalex.org/W2963341956","https://openalex.org/W2970641574","https://openalex.org/W2982153178","https://openalex.org/W2983697263","https://openalex.org/W3006490141","https://openalex.org/W3026089751","https://openalex.org/W3100850545","https://openalex.org/W3123709248","https://openalex.org/W3171153522","https://openalex.org/W3185277860","https://openalex.org/W3192495122","https://openalex.org/W4221161865","https://openalex.org/W4242973245","https://openalex.org/W4313034175","https://openalex.org/W6804656293","https://openalex.org/W6968310603"],"related_works":["https://openalex.org/W2131202893","https://openalex.org/W1599956645","https://openalex.org/W1571620815","https://openalex.org/W276674717","https://openalex.org/W2342941919","https://openalex.org/W1978633512","https://openalex.org/W2152748974","https://openalex.org/W1596157974","https://openalex.org/W2346890250","https://openalex.org/W3198965343"],"abstract_inverted_index":{"In":[0,35,52],"this":[1],"paper,":[2],"we":[3,38,62],"investigate":[4],"the":[5,8,29,40,76,113,117],"applicability":[6],"of":[7,31,72,78,88,95,116,124],"Active":[9,41],"Learning":[10,42],"technique":[11],"to":[12,28,81,109,139],"text":[13,32,89],"clustering":[14,79],"and":[15,59,104,111,144],"topic":[16],"modeling":[17],"tasks.":[18],"The":[19,126],"aforementioned":[20],"problems":[21],"are":[22],"often":[23],"a":[24,53,66,85,93,121,132,150],"non-trivial":[25],"task":[26],"due":[27],"ambiguity":[30],"similarity":[33],"meaning.":[34],"our":[36],"experiments,":[37],"implemented":[39],"approach":[43,135],"using":[44],"automatic":[45],"annotation":[46],"from":[47],"datasets":[48],"with":[49,120,131],"prepared":[50],"labels.":[51],"simulated":[54],"study":[55],"conducted":[56],"on":[57,84],"Polish":[58],"English":[60],"datasets,":[61],"show":[63,129],"how":[64],"labeling":[65],"relatively":[67,133],"small":[68],"carefully":[69],"selected":[70],"number":[71,94,123],"examples":[73],"can":[74],"improve":[75],"quality":[77,115,142],"relative":[80],"approaches":[82,106],"based":[83],"general":[86],"notion":[87],"similarity.":[90],"We":[91],"compare":[92,110],"techniques":[96],"for":[97,100],"selecting":[98],"samples":[99],"labeling,":[101],"dimensionality":[102],"reduction":[103],"training":[105],"in":[107,149],"order":[108],"obtain":[112,140],"best":[114],"resulting":[118],"clusters":[119,143],"minimum":[122],"annotations.":[125],"obtained":[127],"results":[128],"that":[130],"simple":[134],"it":[136],"is":[137],"possible":[138],"good":[141],"thus":[145],"develop":[146],"classification":[147],"ontologies":[148],"data-centric":[151],"approach.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-11-23T00:00:00"}