{"id":"https://openalex.org/W4319165967","doi":"https://doi.org/10.1109/bigdata55660.2022.10020698","title":"Predefined domain specific embeddings of food concepts and recipes: A case study on heterogeneous recipe datasets","display_name":"Predefined domain specific embeddings of food concepts and recipes: A case study on heterogeneous recipe datasets","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4319165967","doi":"https://doi.org/10.1109/bigdata55660.2022.10020698"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020698","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020698","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.01005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005841907","display_name":"Gordana Ispirova","orcid":"https://orcid.org/0000-0001-8558-6909"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Gordana Ispirova","raw_affiliation_strings":["Jožef Stefan Institute,Computer Systems Department,Ljubljana,Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jožef Stefan Institute,Computer Systems Department,Ljubljana,Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082115266","display_name":"Tome Eftimov","orcid":"https://orcid.org/0000-0001-7330-1902"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Tome Eftimov","raw_affiliation_strings":["Jožef Stefan Institute,Computer Systems Department,Ljubljana,Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jožef Stefan Institute,Computer Systems Department,Ljubljana,Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076065873","display_name":"Barbara Korou\u0161i\u0107 Seljak","orcid":"https://orcid.org/0000-0001-7597-2590"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Barbara Korousic Seljak","raw_affiliation_strings":["Jožef Stefan Institute,Computer Systems,Ljubljana,Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jožef Stefan Institute,Computer Systems,Ljubljana,Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3006985408"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4074","last_page":"4083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9743000268936157,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9743000268936157,"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"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9643999934196472,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9621999859809875,"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/recipe","display_name":"Recipe","score":0.9921165704727173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.751946747303009},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6457861661911011},{"id":"https://openalex.org/keywords/ingredient","display_name":"Ingredient","score":0.5936416983604431},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5913345217704773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5344440340995789},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.5277367830276489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4948870539665222},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.46857666969299316},{"id":"https://openalex.org/keywords/publication","display_name":"Publication","score":0.46576452255249023},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4404483437538147},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4183039963245392},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.41289329528808594},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40650254487991333},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3855382204055786},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3225941061973572},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17679649591445923},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1311895251274109},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10876232385635376}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.9921165704727173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751946747303009},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6457861661911011},{"id":"https://openalex.org/C2780589914","wikidata":"https://www.wikidata.org/wiki/Q10675206","display_name":"Ingredient","level":2,"score":0.5936416983604431},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5913345217704773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5344440340995789},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.5277367830276489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4948870539665222},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.46857666969299316},{"id":"https://openalex.org/C41458344","wikidata":"https://www.wikidata.org/wiki/Q732577","display_name":"Publication","level":2,"score":0.46576452255249023},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4404483437538147},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4183039963245392},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.41289329528808594},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40650254487991333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3855382204055786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3225941061973572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17679649591445923},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1311895251274109},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10876232385635376},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C31903555","wikidata":"https://www.wikidata.org/wiki/Q1637030","display_name":"Food science","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020698","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020698","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:dirros.openscience.si:IzpisGradiva.php?id=16366","is_oa":false,"landing_page_url":"https://dirros.openscience.si/IzpisGradiva.php?id=16366","pdf_url":null,"source":{"id":"https://openalex.org/S4377196363","display_name":"DiRROS repository (University of Maribor)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I37696226","host_organization_name":"University of Maribor","host_organization_lineage":["https://openalex.org/I37696226"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings, pp. 4074-4083, 2022.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:2302.01005","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.01005","pdf_url":"https://arxiv.org/pdf/2302.01005","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.01005","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.01005","pdf_url":"https://arxiv.org/pdf/2302.01005","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319165967.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W1686810756","https://openalex.org/W2101234009","https://openalex.org/W2108598243","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2284851926","https://openalex.org/W2557738935","https://openalex.org/W2559582770","https://openalex.org/W2618498494","https://openalex.org/W2737041163","https://openalex.org/W2798397499","https://openalex.org/W2963026768","https://openalex.org/W2963055199","https://openalex.org/W2963997278","https://openalex.org/W2997522493","https://openalex.org/W3080321944","https://openalex.org/W3093106447","https://openalex.org/W3137684688","https://openalex.org/W3139166081","https://openalex.org/W3193903729","https://openalex.org/W3210289208","https://openalex.org/W4214734596","https://openalex.org/W4230432148","https://openalex.org/W4235345631","https://openalex.org/W4238369423","https://openalex.org/W4239072543","https://openalex.org/W4285606949","https://openalex.org/W4294170691","https://openalex.org/W4294808319","https://openalex.org/W4298343974","https://openalex.org/W4302391362","https://openalex.org/W4376539846","https://openalex.org/W4376561267","https://openalex.org/W6636915900","https://openalex.org/W6637373629"],"related_works":["https://openalex.org/W2909050333","https://openalex.org/W2611971073","https://openalex.org/W2011684307","https://openalex.org/W2950291079","https://openalex.org/W2512497230","https://openalex.org/W4288389006","https://openalex.org/W2124095343","https://openalex.org/W3168874191","https://openalex.org/W2065710407","https://openalex.org/W2765707332"],"abstract_inverted_index":{"Although":[0],"recipe":[1,18,68,167,172],"data":[2,78,104],"are":[3,36,132,154],"very":[4],"easy":[5],"to":[6,14,53,87],"come":[7],"by":[8],"nowadays,":[9],"it":[10],"is":[11,146,177],"really":[12],"hard":[13],"find":[15],"a":[16,93],"complete":[17],"dataset":[19,145,173],"\u2013":[20,142,157],"with":[21,51,159,165],"list":[22,127],"of":[23,62,84,128],"ingredients,":[24,28,129],"nutrient":[25,99],"values":[26],"per":[27,30],"and":[29,46,59,75,163],"recipe,":[31],"allergens,":[32],"etc.":[33],"Recipe":[34],"datasets":[35,86],"usually":[37],"collected":[38],"from":[39,150,181],"social":[40],"media":[41],"websites":[42],"where":[43],"users":[44],"post":[45],"publish":[47],"recipes.":[48],"Usually":[49],"written":[50],"little":[52],"no":[54],"structure,":[55],"using":[56,106,120,134,191],"both":[57],"standardized":[58],"non-standardized":[60],"units":[61],"measurement.":[63],"We":[64],"collect":[65],"six":[66,171],"different":[67,73,80],"datasets,":[69],"publicly":[70],"available,":[71],"in":[72,79],"formats":[74],"some":[76],"including":[77],"languages.":[81],"Bringing":[82],"all":[83,140,170],"these":[85],"the":[88,126,135,174,188,192,199],"needed":[89],"format":[90],"for":[91,98,139],"applying":[92],"machine":[94],"learning":[95],"(ML)":[96],"pipeline":[97,176],"prediction":[100],"[1],":[101],"[2],":[102],"includes":[103],"normalization":[105,152],"dictionary":[107],"based":[108,114],"named":[109],"entity":[110],"recognition":[111],"(NER),":[112],"rule":[113],"NER,":[115],"as":[116,118],"well":[117],"conversions":[119],"external":[121],"domain":[122,193],"specific":[123],"resources.":[124],"From":[125],"domain-specific":[130],"embeddings":[131,162,189],"created":[133],"same":[136],"embedding":[137],"space":[138],"recipes":[141],"one":[143,158,164],"ingredient":[144,161],"generated.":[147],"The":[148,179],"result":[149],"this":[151,182],"process":[153],"two":[155],"corpora":[156],"predefined":[160,166],"embeddings.":[168],"On":[169],"ML":[175],"evaluated.":[178],"results":[180,197],"use":[183],"case":[184],"also":[185],"confirm":[186],"that":[187],"merged":[190],"heuristic":[194],"yield":[195],"better":[196],"than":[198],"baselines.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}