{"id":"https://openalex.org/W4403723818","doi":"https://doi.org/10.1109/dsaa61799.2024.10722805","title":"Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting","display_name":"Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4403723818","doi":"https://doi.org/10.1109/dsaa61799.2024.10722805"},"language":"en","primary_location":{"id":"doi:10.1109/dsaa61799.2024.10722805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa61799.2024.10722805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 11th International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5053499526","display_name":"Polina Proskura","orcid":"https://orcid.org/0000-0002-6055-1854"},"institutions":[{"id":"https://openalex.org/I4210107660","display_name":"Institute for Information Transmission Problems","ror":"https://ror.org/013w2d378","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210107660"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Polina Proskura","raw_affiliation_strings":["Institute for Information Transmission Problems,Moscow,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Information Transmission Problems,Moscow,Russia","institution_ids":["https://openalex.org/I4210107660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011905327","display_name":"Alexey Zaytsev","orcid":"https://orcid.org/0000-0002-1653-0204"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexey Zaytsev","raw_affiliation_strings":["Skolkovo Institute of Science and Technology Risk Management, Sber,Moscow,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology Risk Management, Sber,Moscow,Russia","institution_ids":["https://openalex.org/I125989756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6814,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67866616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.7013999819755554,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.7013999819755554,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/weighting","display_name":"Weighting","score":0.8081108331680298},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.7328695058822632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6920002698898315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6116440892219543},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41299062967300415},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4124603569507599},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.406823992729187},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33391863107681274},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06689444184303284}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8081108331680298},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.7328695058822632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920002698898315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116440892219543},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41299062967300415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4124603569507599},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.406823992729187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33391863107681274},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06689444184303284},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/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/dsaa61799.2024.10722805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa61799.2024.10722805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 11th International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2805551362","display_name":null,"funder_award_id":"20-7110135","funder_id":"https://openalex.org/F4320324099","funder_display_name":"Russian Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320324099","display_name":"Russian Science Foundation","ror":"https://ror.org/03y2gwe85"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2014440499","https://openalex.org/W2164921999","https://openalex.org/W2784332447","https://openalex.org/W2912934387","https://openalex.org/W2964030506","https://openalex.org/W2967602207","https://openalex.org/W2978670439","https://openalex.org/W2982027034","https://openalex.org/W2999791086","https://openalex.org/W3034403194","https://openalex.org/W3110217478","https://openalex.org/W3128376221","https://openalex.org/W3149839747","https://openalex.org/W3153723500","https://openalex.org/W3162754606","https://openalex.org/W3201369838","https://openalex.org/W4250589301","https://openalex.org/W4285143611","https://openalex.org/W4285298706","https://openalex.org/W4318677156","https://openalex.org/W4384068188","https://openalex.org/W4385191275","https://openalex.org/W4385573323","https://openalex.org/W4385573450","https://openalex.org/W4385574115","https://openalex.org/W6605323724","https://openalex.org/W6691459498","https://openalex.org/W6748173244","https://openalex.org/W6749107692","https://openalex.org/W6754772488","https://openalex.org/W6755977528","https://openalex.org/W6761472960","https://openalex.org/W6768851824","https://openalex.org/W6777834095","https://openalex.org/W6778631989","https://openalex.org/W6780820450","https://openalex.org/W6803092309","https://openalex.org/W6810347613"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2040545019","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W4206560911"],"abstract_inverted_index":{"In":[0,12],"machine":[1],"learning,":[2],"ensembles":[3,17,44,66],"are":[4],"important":[5],"tools":[6],"for":[7,48,65,102],"improving":[8],"the":[9,19,54],"model":[10],"performance.":[11],"natural":[13],"language":[14],"processing":[15],"specifically,":[16],"boost":[18],"performance":[20,77],"of":[21,41,58,67,74],"a":[22],"method":[23],"due":[24],"to":[25,62,82],"multiple":[26],"large":[27],"models":[28,69],"available":[29],"in":[30,53],"open":[31],"source.":[32],"However,":[33],"existing":[34],"approaches":[35],"mostly":[36],"rely":[37],"on":[38,90],"simple":[39],"averaging":[40],"predictions":[42],"by":[43],"with":[45],"equal":[46],"weights":[47,64],"each":[49,83],"model,":[50],"ignoring":[51],"differences":[52],"quality":[55,100],"and":[56,107],"conformity":[57],"models.":[59],"We":[60],"propose":[61],"estimate":[63],"NLP":[68],"using":[70],"not":[71],"only":[72],"knowledge":[73],"their":[75,80],"individual":[76],"but":[78],"also":[79],"similarity":[81],"other.":[84],"By":[85],"adopting":[86],"distance":[87],"measures":[88],"based":[89],"Topological":[91],"Data":[92],"Analysis":[93],"(TDA),":[94],"we":[95],"improve":[96],"our":[97],"ensemble.":[98],"The":[99],"improves":[101],"both":[103],"text":[104],"classification":[105],"accuracy":[106],"relevant":[108],"uncertainty":[109],"estimation.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}