{"id":"https://openalex.org/W4412889419","doi":"https://doi.org/10.18653/v1/2025.acl-srw.55","title":"Semantic alignment in hyperbolic space for fine-grained emotion classification","display_name":"Semantic alignment in hyperbolic space for fine-grained emotion classification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889419","doi":"https://doi.org/10.18653/v1/2025.acl-srw.55"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-srw.55","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.55","pdf_url":"https://aclanthology.org/2025.acl-srw.55.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.55.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102847787","display_name":"Ashish Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ashish Kumar","raw_affiliation_strings":["Indian Institute of Technology Roorkee , Roorkee , India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee , Roorkee , India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082753354","display_name":"Durga Toshniwal","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Durga Toshniwal","raw_affiliation_strings":["Indian Institute of Technology Roorkee , Roorkee , India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee , Roorkee , India","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102847787"],"corresponding_institution_ids":["https://openalex.org/I154851008"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16679321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"806","last_page":"813"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.7414000034332275,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.7414000034332275,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.7366999983787537,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7347999811172485,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.6411663293838501},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.6221863031387329},{"id":"https://openalex.org/keywords/hyperbolic-space","display_name":"Hyperbolic space","score":0.5345520377159119},{"id":"https://openalex.org/keywords/semantic-space","display_name":"Semantic space","score":0.4959770143032074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47255322337150574},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3636888265609741},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16648250818252563},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.15531089901924133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6411663293838501},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.6221863031387329},{"id":"https://openalex.org/C83677898","wikidata":"https://www.wikidata.org/wiki/Q1878538","display_name":"Hyperbolic space","level":2,"score":0.5345520377159119},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.4959770143032074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47255322337150574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3636888265609741},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16648250818252563},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.15531089901924133},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-srw.55","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.55","pdf_url":"https://aclanthology.org/2025.acl-srw.55.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.55","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.55","pdf_url":"https://aclanthology.org/2025.acl-srw.55.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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889419.pdf","grobid_xml":"https://content.openalex.org/works/W4412889419.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W3177428197","https://openalex.org/W4393399846"],"related_works":["https://openalex.org/W1608408498","https://openalex.org/W4226494630","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W3204019825","https://openalex.org/W4382323493","https://openalex.org/W4385570850"],"abstract_inverted_index":{"Existing":[0],"approaches":[1],"to":[2,19,35,102,107,124],"fine-grained":[3,37],"emotion":[4,23],"classification":[5],"(FEC)":[6],"often":[7],"operate":[8],"in":[9],"Euclidean":[10],"space,":[11],"where":[12],"the":[13,17,55,78,94,122,156],"flat":[14],"geometry":[15,34],"limits":[16],"ability":[18],"distinguish":[20],"semantically":[21,48,118],"similar":[22,49,119],"labels":[24,51,110],"(e.g.,":[25],"annoyed":[26],"vs.":[27],"angry).While":[28],"prior":[29],"research":[30],"has":[31],"explored":[32],"hyperbolic":[33,82,91],"capture":[36],"label":[38,88,126],"distinctions,":[39],"it":[40],"typically":[41],"relies":[42],"on":[43,130,150],"predefined":[44,132],"hierarchies":[45],"and":[46,87,97,134,145],"ignores":[47],"negative":[50,147],"that":[52,76],"can":[53],"mislead":[54],"model":[56,80,123],"into":[57,90],"making":[58],"incorrect":[59],"predictions.In":[60],"this":[61],"work,":[62],"we":[63],"propose":[64],"HyCoEM":[65],"(Hyperbolic":[66],"Contrastive":[67],"Learning":[68],"for":[69],"Emotion":[70],"Classification),":[71],"a":[72,99,131],"semantic":[73],"alignment":[74],"framework":[75],"leverages":[77],"Lorentz":[79],"of":[81,158],"space.Our":[83],"approach":[84,160],"embeds":[85],"text":[86,104],"representations":[89],"space":[92],"via":[93],"exponential":[95],"map,":[96],"employs":[98],"contrastive":[100],"loss":[101],"bring":[103],"embeddings":[105,127],"closer":[106],"their":[108],"true":[109],"while":[111],"pushing":[112],"them":[113],"away":[114],"from":[115,142],"adaptively":[116],"selected,":[117],"negatives.This":[120],"enables":[121],"learn":[125],"without":[128],"relying":[129],"hierarchy":[133],"better":[135],"captures":[136],"subtle":[137],"distinctions":[138],"by":[139],"incorporating":[140],"information":[141],"both":[143],"positive":[144],"challenging":[146],"labels.Experimental":[148],"results":[149],"two":[151],"benchmark":[152],"FEC":[153],"datasets":[154],"demonstrate":[155],"effectiveness":[157],"our":[159],"over":[161],"baseline":[162],"methods.":[163],"1":[164]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}