{"id":"https://openalex.org/W4200430816","doi":"https://doi.org/10.1007/s10844-021-00693-2","title":"Hierarchy-based semantic embeddings for single-valued & multi-valued categorical variables","display_name":"Hierarchy-based semantic embeddings for single-valued & multi-valued categorical variables","publication_year":2021,"publication_date":"2021-12-28","ids":{"openalex":"https://openalex.org/W4200430816","doi":"https://doi.org/10.1007/s10844-021-00693-2"},"language":"en","primary_location":{"id":"doi:10.1007/s10844-021-00693-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-021-00693-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10844-021-00693-2.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10844-021-00693-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034963323","display_name":"Summaya Mumtaz","orcid":"https://orcid.org/0000-0002-7594-3076"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Summaya Mumtaz","raw_affiliation_strings":["University of Oslo, Oslo, Norway","University of Oslo, Gaustadall\u00e9en 23B, 0373, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-7594-3076","affiliations":[{"raw_affiliation_string":"University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"University of Oslo, Gaustadall\u00e9en 23B, 0373, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103175558","display_name":"Martin Giese","orcid":"https://orcid.org/0000-0002-2058-2728"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Martin Giese","raw_affiliation_strings":["University of Oslo, Oslo, Norway","University of Oslo, Gaustadall\u00e9en 23B, 0373, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"University of Oslo, Gaustadall\u00e9en 23B, 0373, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034963323","https://openalex.org/A5103175558"],"corresponding_institution_ids":["https://openalex.org/I184942183"],"apc_list":{"value":2490,"currency":"EUR","value_usd":3090},"apc_paid":{"value":2490,"currency":"EUR","value_usd":3090},"fwci":1.399,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85401027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"58","issue":"3","first_page":"613","last_page":"640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9932000041007996,"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":0.9897000193595886,"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/categorical-variable","display_name":"Categorical variable","score":0.799869179725647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7780004739761353},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5905096530914307},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5857216715812683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5839285254478455},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.5608190298080444},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5199257731437683},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.48683542013168335},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.479739785194397},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.4773673713207245},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4770333468914032},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.42783811688423157},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4221186637878418},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39385029673576355},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3809517025947571}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.799869179725647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780004739761353},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5905096530914307},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5857216715812683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5839285254478455},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.5608190298080444},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5199257731437683},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.48683542013168335},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.479739785194397},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.4773673713207245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4770333468914032},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.42783811688423157},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4221186637878418},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39385029673576355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3809517025947571},{"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/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10844-021-00693-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-021-00693-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10844-021-00693-2.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10844-021-00693-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-021-00693-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10844-021-00693-2.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G8281449386","display_name":null,"funder_award_id":"237898","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"}],"funders":[{"id":"https://openalex.org/F4320323260","display_name":"Universitetet i Oslo","ror":"https://ror.org/01xtthb56"},{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200430816.pdf","grobid_xml":"https://content.openalex.org/works/W4200430816.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W60493759","https://openalex.org/W89242458","https://openalex.org/W1516154272","https://openalex.org/W1553518941","https://openalex.org/W1571447506","https://openalex.org/W1578620296","https://openalex.org/W1597533344","https://openalex.org/W1614298861","https://openalex.org/W1659833910","https://openalex.org/W1742842785","https://openalex.org/W1806783651","https://openalex.org/W1923180085","https://openalex.org/W1926956132","https://openalex.org/W1990836268","https://openalex.org/W1994292711","https://openalex.org/W2047878524","https://openalex.org/W2080100102","https://openalex.org/W2084377579","https://openalex.org/W2100935296","https://openalex.org/W2103318667","https://openalex.org/W2111685427","https://openalex.org/W2117805756","https://openalex.org/W2135964261","https://openalex.org/W2140480387","https://openalex.org/W2140898374","https://openalex.org/W2141628941","https://openalex.org/W2148143831","https://openalex.org/W2153579005","https://openalex.org/W2163952039","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2396881363","https://openalex.org/W2509960255","https://openalex.org/W2534712034","https://openalex.org/W2757933620","https://openalex.org/W2765449478","https://openalex.org/W2783777501","https://openalex.org/W2806031239","https://openalex.org/W2811024573","https://openalex.org/W2884238387","https://openalex.org/W2889198823","https://openalex.org/W2947817682","https://openalex.org/W2954052001","https://openalex.org/W2954671964","https://openalex.org/W2954699761","https://openalex.org/W2956530858","https://openalex.org/W2963105378","https://openalex.org/W2982781344","https://openalex.org/W3032078672","https://openalex.org/W3105248300","https://openalex.org/W3216404684","https://openalex.org/W4213009331","https://openalex.org/W4292402161","https://openalex.org/W6606879723","https://openalex.org/W6636975626","https://openalex.org/W6732539909","https://openalex.org/W6991854852","https://openalex.org/W7054800020"],"related_works":["https://openalex.org/W2600595669","https://openalex.org/W2358805260","https://openalex.org/W2106251529","https://openalex.org/W2382778002","https://openalex.org/W2887442125","https://openalex.org/W3113012686","https://openalex.org/W2566841210","https://openalex.org/W2493311319","https://openalex.org/W2782711951","https://openalex.org/W4200430816"],"abstract_inverted_index":{"Abstract":[0],"In":[1,30],"low-resource":[2],"domains,":[3],"it":[4],"is":[5,65,132,208,272],"challenging":[6],"to":[7,17,40,93,104,133,166,252],"achieve":[8],"good":[9],"performance":[10,235,255,266],"using":[11,109,214,241,275],"existing":[12,194,221],"machine":[13,41,95],"learning":[14,42,96],"methods":[15,222],"due":[16],"a":[18,38,83,126,136,147,168,201,249],"lack":[19],"of":[20,60,89,121,128,256,267],"training":[21,50,78],"data":[22,25,54],"and":[23,28,47,179,227,259],"mixed":[24],"types":[26],"(numeric":[27],"categorical).":[29],"particular,":[31],"categorical":[32,112,181],"variables":[33,113],"with":[34,99,197,220],"high":[35],"cardinality":[36],"pose":[37],"challenge":[39,107],"tasks":[43,239,271],"such":[44,223],"as":[45,224],"classification":[46,270],"regression":[48],"because":[49],"requires":[51],"sufficiently":[52],"many":[53],"points":[55],"for":[56,72,111,177],"the":[57,77,90,144,156,254,268],"possible":[58],"values":[59,73],"each":[61],"variable.":[62],"Since":[63],"interpolation":[64],"not":[66,74],"possible,":[67],"nothing":[68],"can":[69,158],"be":[70,159],"learned":[71],"seen":[75],"in":[76,97,265],"set.":[79],"This":[80,207],"paper":[81],"presents":[82],"method":[84],"that":[85,114,163],"uses":[86,248],"prior":[87],"knowledge":[88,123],"application":[91],"domain":[92,122],"support":[94],"cases":[98],"insufficient":[100],"data.":[101,182],"We":[102,172,183,191],"propose":[103,146,173],"address":[105],"this":[106],"by":[108,210,274],"embeddings":[110,213,229,258],"are":[115],"based":[116,142],"on":[117,143,186,200,230,236],"an":[118],"explicit":[119],"representation":[120],"(KR),":[124],"namely":[125],"hierarchy":[127],"concepts.":[129],"Our":[130],"approach":[131,199],"1.":[134],"define":[135,167],"semantic":[137,276],"similarity":[138,153,164,195,204,216],"measure":[139,165],"between":[140],"categories,":[141],"hierarchy\u2014we":[145],"purely":[148],"hierarchy-based":[149],"measure,":[150],"but":[151],"other":[152],"measures":[154],"from":[155],"literature":[157],"used\u2014and":[160],"2.":[161],"use":[162,189,205,246],"modified":[169],"one-hot":[170],"encoding.":[171],"two":[174],"embedding":[175],"schemes":[176],"single-valued":[178],"multi-valued":[180],"perform":[184],"experiments":[185],"three":[187],"different":[188,215],"cases.":[190],"first":[192],"compare":[193,253],"approaches":[196],"our":[198],"word":[202,212],"pair":[203],"case.":[206],"followed":[209],"creating":[211],"approaches.":[217],"A":[218],"comparison":[219],"Google,":[225],"Word2Vec":[226],"GloVe":[228],"several":[231],"benchmarks":[232],"shows":[233],"better":[234],"concept":[237],"categorisation":[238],"when":[240],"knowledge-based":[242],"embeddings.":[243],"The":[244],"third":[245],"case":[247],"medical":[250],"dataset":[251],"semantic-based":[257],"standard":[260],"binary":[261],"encodings.":[262],"Significant":[263],"improvement":[264],"downstream":[269],"achieved":[273],"information.":[277]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-18T08:10:14.011955","created_date":"2025-10-10T00:00:00"}