{"id":"https://openalex.org/W4412889370","doi":"https://doi.org/10.18653/v1/2025.acl-srw.52","title":"CoLeM: A framework for semantic interpretation of Russian-language tables based on contrastive learning","display_name":"CoLeM: A framework for semantic interpretation of Russian-language tables based on contrastive learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889370","doi":"https://doi.org/10.18653/v1/2025.acl-srw.52"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-srw.52","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.52","pdf_url":"https://aclanthology.org/2025.acl-srw.52.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-srw.52.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010311929","display_name":"Kirill V. Tobola","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kirill Tobola","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5022770117","display_name":"Nikita O. Dorodnykh","orcid":"https://orcid.org/0000-0001-7794-4462"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikita Dorodnykh","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010311929"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23400993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"784","last_page":"794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9629999995231628,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9629999995231628,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14280","display_name":"Big Data Technologies and Applications","score":0.917900025844574,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7858043909072876},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7255998253822327},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.6456888914108276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6116182804107666},{"id":"https://openalex.org/keywords/semantic-interpretation","display_name":"Semantic interpretation","score":0.5389739871025085},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.48726406693458557},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18214544653892517},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07899335026741028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858043909072876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7255998253822327},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.6456888914108276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116182804107666},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.5389739871025085},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.48726406693458557},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18214544653892517},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07899335026741028}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-srw.52","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.52","pdf_url":"https://aclanthology.org/2025.acl-srw.52.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-srw.52","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.52","pdf_url":"https://aclanthology.org/2025.acl-srw.52.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324632","display_name":"Ministero dello Sviluppo Economico","ror":"https://ror.org/011z3ff80"},{"id":"https://openalex.org/F4320334801","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889370.pdf","grobid_xml":"https://content.openalex.org/works/W4412889370.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2017284154","https://openalex.org/W2004663191","https://openalex.org/W2603623739","https://openalex.org/W2950298502","https://openalex.org/W2250477996","https://openalex.org/W2891979318","https://openalex.org/W3034934889","https://openalex.org/W2116915753","https://openalex.org/W2149305584"],"abstract_inverted_index":{"Tables":[0],"are":[1,102],"extensively":[2],"utilized":[3],"to":[4,42,55],"represent":[5],"and":[6,46,61,82,118,140],"store":[7],"data,":[8],"however,":[9],"they":[10],"often":[11],"lack":[12],"explicit":[13,161],"semantics":[14],"necessary":[15],"for":[16,26,68,77,167],"machine":[17],"interpretation":[18,23],"of":[19,65,116,122,132,144],"their":[20],"contents.Semantic":[21],"table":[22,100],"is":[24,164],"essential":[25],"integrating":[27],"structured":[28],"data":[29,45,79,138,169],"with":[30,38],"knowledge":[31],"graphs,":[32],"yet":[33],"existing":[34],"methods":[35],"face":[36],"challenges":[37],"Russian-language":[39],"tables":[40],"due":[41],"limited":[43],"labeled":[44],"linguistic":[47],"peculiarities.This":[48],"paper":[49],"introduces":[50],"a":[51,84,113,119],"contrastive":[52,75,152],"learning":[53,76,153],"approach":[54],"minimize":[56],"reliance":[57],"on":[58,90],"manual":[59],"labeling":[60],"enhance":[62],"the":[63,91,105,130,133,145],"accuracy":[64],"column":[66],"annotation":[67],"rare":[69,168],"semantic":[70,156],"types.The":[71],"proposed":[72,134],"method":[73,135],"adapts":[74],"tabular":[78],"through":[80],"augmentations":[81],"employs":[83],"distilled":[85],"multilingual":[86],"BERT":[87],"model":[88],"trained":[89],"unlabeled":[92],"RWT":[93],"corpus":[94],"(comprising":[95],"7.4":[96],"million":[97],"columns).The":[98],"resulting":[99],"representations":[101],"incorporated":[103],"into":[104],"RuTaBERT":[106],"pipeline,":[107],"reducing":[108],"computational":[109],"overhead.Experimental":[110],"results":[111,148],"demonstrate":[112],"micro-F1":[114],"score":[115,121],"97%":[117],"macro-F1":[120],"92%,":[123],"surpassing":[124],"several":[125],"baseline":[126],"approaches.These":[127],"findings":[128],"emphasize":[129],"efficiency":[131],"in":[136],"addressing":[137],"sparsity":[139],"handling":[141],"unique":[142],"features":[143],"Russian":[146],"language.The":[147],"further":[149],"confirm":[150],"that":[151],"effectively":[154],"captures":[155],"similarities":[157],"among":[158],"columns":[159],"without":[160],"supervision,":[162],"which":[163],"particularly":[165],"vital":[166],"types.":[170]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}