{"id":"https://openalex.org/W4393157285","doi":"https://doi.org/10.1609/aaai.v38i21.30307","title":"Some Like It Small: Czech Semantic Embedding Models for Industry Applications","display_name":"Some Like It Small: Czech Semantic Embedding Models for Industry Applications","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393157285","doi":"https://doi.org/10.1609/aaai.v38i21.30307"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i21.30307","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30307/32315","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30307/32315","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108316330","display_name":"Ji\u0159\u00ed Bedn\u00e1\u0159","orcid":null},"institutions":[{"id":"https://openalex.org/I143544115","display_name":"Snam (Italy)","ror":"https://ror.org/04g2nab09","country_code":"IT","type":"company","lineage":["https://openalex.org/I143544115"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ji\u0159\u00ed Bedn\u00e1\u0159","raw_affiliation_strings":["Seznam.cz"],"affiliations":[{"raw_affiliation_string":"Seznam.cz","institution_ids":["https://openalex.org/I143544115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032425414","display_name":"Jakub N\u00e1plava","orcid":"https://orcid.org/0000-0003-2259-1377"},"institutions":[{"id":"https://openalex.org/I143544115","display_name":"Snam (Italy)","ror":"https://ror.org/04g2nab09","country_code":"IT","type":"company","lineage":["https://openalex.org/I143544115"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Jakub N\u00e1plava","raw_affiliation_strings":["Seznam.cz"],"affiliations":[{"raw_affiliation_string":"Seznam.cz","institution_ids":["https://openalex.org/I143544115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074150569","display_name":"Petra Baran\u010d\u00edkov\u00e1","orcid":"https://orcid.org/0000-0002-4070-2766"},"institutions":[{"id":"https://openalex.org/I143544115","display_name":"Snam (Italy)","ror":"https://ror.org/04g2nab09","country_code":"IT","type":"company","lineage":["https://openalex.org/I143544115"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Petra Baran\u010d\u00edkov\u00e1","raw_affiliation_strings":["Seznam.cz"],"affiliations":[{"raw_affiliation_string":"Seznam.cz","institution_ids":["https://openalex.org/I143544115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009852523","display_name":"Ond\u0159ej Lisick\u00fd","orcid":"https://orcid.org/0000-0001-7943-4140"},"institutions":[{"id":"https://openalex.org/I143544115","display_name":"Snam (Italy)","ror":"https://ror.org/04g2nab09","country_code":"IT","type":"company","lineage":["https://openalex.org/I143544115"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ond\u0159ej Lisick\u00fd","raw_affiliation_strings":["Seznam.cz"],"affiliations":[{"raw_affiliation_string":"Seznam.cz","institution_ids":["https://openalex.org/I143544115"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":84},"biblio":{"volume":"38","issue":"21","first_page":"22734","last_page":"22742"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9487,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9455,"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":[],"concepts":[{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.8706862},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.60211825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.56074315},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.32276005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26119637},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.118490994},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i21.30307","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30307/32315","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2311.13921","pdf_url":"https://arxiv.org/pdf/2311.13921","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i21.30307","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/30307/32315","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.42,"display_name":"Industry, innovation and infrastructure"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W2250805461","https://openalex.org/W2493916176","https://openalex.org/W2790235966","https://openalex.org/W2891976145","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2963263347","https://openalex.org/W2964022491","https://openalex.org/W2970641574","https://openalex.org/W3016473712","https://openalex.org/W3034439313","https://openalex.org/W3035016936","https://openalex.org/W3039695075","https://openalex.org/W3082929539","https://openalex.org/W3100806282","https://openalex.org/W3156636935","https://openalex.org/W3166396011","https://openalex.org/W3168875417","https://openalex.org/W3192478068","https://openalex.org/W3203765809","https://openalex.org/W3207988762","https://openalex.org/W3212725701","https://openalex.org/W3214520975","https://openalex.org/W4206121183","https://openalex.org/W4221152199","https://openalex.org/W4224313754","https://openalex.org/W4246183800","https://openalex.org/W4283790703","https://openalex.org/W4286959591","https://openalex.org/W4287727391","https://openalex.org/W4287824654","https://openalex.org/W4290943593","https://openalex.org/W4295253515","https://openalex.org/W4324016655","https://openalex.org/W4385570895","https://openalex.org/W4385571915","https://openalex.org/W4385572770","https://openalex.org/W4385574084","https://openalex.org/W4386576685","https://openalex.org/W4389921502"],"related_works":["https://openalex.org/W874599710","https://openalex.org/W578757760","https://openalex.org/W4378675964","https://openalex.org/W4360856886","https://openalex.org/W305958151","https://openalex.org/W2782410293","https://openalex.org/W2748952813","https://openalex.org/W2724504120","https://openalex.org/W2614400517","https://openalex.org/W1485297680"],"abstract_inverted_index":{"This":[0,136],"article":[1,98],"focuses":[2],"on":[3],"the":[4,27,54,86,89,103,110,122],"development":[5],"and":[6,40,48,71,83,88,133],"evaluation":[7,90],"of":[8,30,57,102],"Small-sized":[9],"Czech":[10,32,111],"sentence":[11,105],"embedding":[12,106],"models.":[13,79],"Small":[14],"models":[15,59,87,107,115],"are":[16,44,51,92],"important":[17],"components":[18],"for":[19,126],"real-time":[20],"industry":[21],"applications":[22,101],"in":[23,108,128],"resource-constrained":[24],"environments.":[25],"Given":[26],"limited":[28],"availability":[29],"labeled":[31],"data,":[33],"alternative":[34],"approaches,":[35],"including":[36],"pre-training,":[37],"knowledge":[38],"distillation,":[39],"unsupervised":[41],"contrastive":[42],"fine-tuning,":[43],"investigated.":[45],"Comprehensive":[46],"intrinsic":[47],"extrinsic":[49],"analyses":[50],"conducted,":[52],"showcasing":[53],"competitive":[55],"performance":[56],"our":[58],"compared":[60],"to":[61],"significantly":[62],"larger":[63],"counterparts,":[64,120],"with":[65],"approximately":[66],"8":[67],"times":[68,73],"smaller":[69],"size":[70],"5":[72],"faster":[74],"speed":[75],"than":[76],"conventional":[77],"Base-sized":[78],"To":[80],"promote":[81],"cooperation":[82],"reproducibility,":[84],"both":[85],"pipeline":[91],"made":[93],"publicly":[94],"accessible.":[95],"Ultimately,":[96],"this":[97],"presents":[99],"practical":[100],"developed":[104],"Seznam.cz,":[109],"search":[112,124],"engine.":[113],"These":[114],"have":[116],"effectively":[117],"replaced":[118],"previous":[119],"enhancing":[121],"overall":[123],"experience":[125],"instance,":[127],"organic":[129],"search,":[130],"featured":[131],"snippets,":[132],"image":[134],"search.":[135],"transition":[137],"has":[138],"yielded":[139],"improved":[140],"performance.":[141]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4393157285","counts_by_year":[],"updated_date":"2024-12-15T13:35:26.967741","created_date":"2024-03-26"}