{"id":"https://openalex.org/W4406264476","doi":"https://doi.org/10.1109/cifer62890.2024.10772793","title":"Financial Semantic Textual Similarity: A New Dataset and Model","display_name":"Financial Semantic Textual Similarity: A New Dataset and Model","publication_year":2024,"publication_date":"2024-10-22","ids":{"openalex":"https://openalex.org/W4406264476","doi":"https://doi.org/10.1109/cifer62890.2024.10772793"},"language":"en","primary_location":{"id":"doi:10.1109/cifer62890.2024.10772793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cifer62890.2024.10772793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101853522","display_name":"Shanshan Yang","orcid":"https://orcid.org/0000-0002-7765-143X"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanshan Yang","raw_affiliation_strings":["School of Business, Stevens Institute of Technology,Hoboken,NJ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Business, Stevens Institute of Technology,Hoboken,NJ,USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080120183","display_name":"Steve Y. Yang","orcid":"https://orcid.org/0000-0002-4816-4720"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steve Yang","raw_affiliation_strings":["School of Business, Stevens Institute of Technology,Hoboken,NJ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Business, Stevens Institute of Technology,Hoboken,NJ,USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088161536","display_name":"Feng Mai","orcid":"https://orcid.org/0000-0001-6897-8935"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng Mai","raw_affiliation_strings":["University of Iowa,Department of Business Analytics,Iowa City,IA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Iowa,Department of Business Analytics,Iowa City,IA,USA","institution_ids":["https://openalex.org/I126307644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3562,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83134542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9814000129699707,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9814000129699707,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6688893437385559},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6343486905097961},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6192212104797363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4300510287284851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4175073504447937},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3652408719062805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688893437385559},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6343486905097961},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6192212104797363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4300510287284851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4175073504447937},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3652408719062805},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cifer62890.2024.10772793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cifer62890.2024.10772793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4376653378","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W3204019825","https://openalex.org/W2176214140","https://openalex.org/W2516873349","https://openalex.org/W4385239468","https://openalex.org/W4200476258","https://openalex.org/W2022470916","https://openalex.org/W3201962287"],"abstract_inverted_index":{"We":[0],"introduce":[1],"FinSTS,":[2,75],"a":[3,58,70,90,105,115],"novel":[4],"dataset":[5],"for":[6,25,43,65],"financial":[7,66,110,127],"semantic":[8,62,123],"textual":[9],"similarity":[10],"(STS),":[11],"comprising":[12],"4,000":[13],"sentence":[14,41],"pairs":[15,42],"from":[16],"earnings":[17],"calls":[18],"and":[19,47,119],"SEC":[20],"filings.":[21],"To":[22],"improve":[23],"models":[24,77,101],"the":[26,126],"Financial":[27],"STS":[28],"task,":[29],"we":[30,55],"propose":[31],"an":[32],"active":[33],"learning":[34],"(AL)":[35],"algorithm":[36],"that":[37,60,78,121],"efficiently":[38],"selects":[39],"informative":[40],"annotation":[44],"by":[45],"GPT-4":[46],"creates":[48],"high-quality":[49],"training":[50],"data.":[51],"Using":[52],"this":[53],"approach,":[54],"train":[56],"FinSentenceBERT,":[57],"model":[59,93,107],"generates":[61],"embeddings":[63],"specifically":[64],"text.":[67,111],"FinSentenceBERT":[68],"establishes":[69],"new":[71],"performance":[72],"benchmark":[73],"on":[74,86,103,109],"outperforming":[76],"use":[79],"basic":[80],"pooling":[81],"strategies":[82],"or":[83],"are":[84],"fine-tuned":[85],"general":[87,91],"datasets.":[88],"Surprisingly,":[89],"SBERT":[92],"trained":[94],"using":[95],"our":[96],"AL":[97],"approach":[98],"surpasses":[99],"even":[100],"based":[102],"FinBERT,":[104],"language":[106],"pre-trained":[108],"Our":[112],"research":[113],"contributes":[114],"specialized":[116,134],"dataset,":[117],"model,":[118],"methodology":[120],"advance":[122],"understanding":[124],"in":[125],"domain,":[128],"with":[129],"potential":[130],"applications":[131],"to":[132],"other":[133],"domains.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}