{"id":"https://openalex.org/W4416035439","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1373","title":"Annotating Training Data for Conditional Semantic Textual Similarity Measurement using Large Language Models","display_name":"Annotating Training Data for Conditional Semantic Textual Similarity Measurement using Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035439","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1373"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1373","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1373","pdf_url":"https://aclanthology.org/2025.emnlp-main.1373.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1373.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058764230","display_name":"Gaifan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gaifan Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100753053","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0003-0020-847X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073503574","display_name":"Danushka Bollegala","orcid":"https://orcid.org/0000-0003-4476-7003"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danushka Bollegala","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058764230"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18278787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27003","last_page":"27015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5131000280380249,"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/T10028","display_name":"Topic Modeling","score":0.5131000280380249,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.06199999898672104,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.054099999368190765,"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/training-set","display_name":"Training set","score":0.4512999951839447},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4447000026702881},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43459999561309814},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4056999981403351},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.39489999413490295},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645000219345093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6452999711036682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6114000082015991},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43459999561309814},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1373","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1373","pdf_url":"https://aclanthology.org/2025.emnlp-main.1373.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1373","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1373","pdf_url":"https://aclanthology.org/2025.emnlp-main.1373.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035439.pdf","grobid_xml":"https://content.openalex.org/works/W4416035439.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Semantic":[0,24],"similarity":[1,33,121],"between":[2,10],"two":[3,41],"sentences":[4,38],"depends":[5],"on":[6,90,157],"the":[7,22,75,96,100,117,124,144],"aspects":[8],"considered":[9],"those":[11],"sentences.To":[12],"study":[13],"this":[14,54,91,104],"phenomenon,":[15],"Deshpande":[16,129],"et":[17,45,130],"al.":[18,46,131],"(":[19,47],"2023)":[20],"proposed":[21,127,133],"Conditional":[23],"Textual":[25],"Similarity":[26],"(C-STS)":[27],"task":[28,92,146],"and":[29,56,79,120,160],"annotated":[30,81],"a":[31,61,85,139,153,165],"human-rated":[32],"dataset":[34,55,126,142],"containing":[35],"pairs":[36],"of":[37,64,77,99],"compared":[39],"under":[40],"different":[42],"conditions.However,":[43],"Tu":[44],"2024)":[48],"found":[49],"various":[50],"annotation":[51],"issues":[52],"in":[53,123,170],"showed":[57],"that":[58],"manually":[59],"re-annotating":[60],"small":[62],"portion":[63],"it":[65],"leads":[66],"to":[67,110,115,137],"more":[68],"accurate":[69],"C-STS":[70,82,101,145,155],"models.Despite":[71],"these":[72],"pioneering":[73],"efforts,":[74],"lack":[76],"large":[78,140],"accurately":[80],"datasets":[83],"remains":[84],"blocker":[86],"for":[87,143],"making":[88],"progress":[89],"as":[93],"evidenced":[94],"by":[95,128,151],"subpar":[97],"performance":[98],"models.To":[102],"address":[103],"training":[105,141,152],"data":[106],"need,":[107],"we":[108,163],"resort":[109],"Large":[111],"Language":[112],"Models":[113],"(LLMs)":[114],"correct":[116],"condition":[118],"statements":[119],"ratings":[122],"original":[125],"(2023).Our":[132],"method":[134],"is":[135],"able":[136],"reannotate":[138],"with":[147],"minimal":[148],"manual":[149],"effort.Importantly,":[150],"supervised":[154],"model":[156],"our":[158],"cleaned":[159],"re-annotated":[161,173],"dataset,":[162],"achieve":[164],"5.4%":[166],"statistically":[167],"significant":[168],"improvement":[169],"Spearman":[171],"correlation.The":[172]},"counts_by_year":[],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-11-08T00:00:00"}