{"id":"https://openalex.org/W4385859634","doi":"https://doi.org/10.1162/tacl_a_00584","title":"Collective Human Opinions in Semantic Textual Similarity","display_name":"Collective Human Opinions in Semantic Textual Similarity","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385859634","doi":"https://doi.org/10.1162/tacl_a_00584"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00584","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00584","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00584/2154408/tacl_a_00584.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00584/2154408/tacl_a_00584.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100631225","display_name":"Yuxia Wang","orcid":"https://orcid.org/0000-0002-6095-1030"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Yuxia Wang","raw_affiliation_strings":["The University of Melbourne, Melbourne, Victoria, Australia. yuxiaw@student.unimelb.edu.au"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Victoria, Australia. yuxiaw@student.unimelb.edu.au","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006709668","display_name":"Shimin Tao","orcid":"https://orcid.org/0000-0002-2795-6921"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shimin Tao","raw_affiliation_strings":["Huawei TSC, Beijing, China. taoshimin@huawei.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei TSC, Beijing, China. taoshimin@huawei.com","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101646797","display_name":"Ning Xie","orcid":"https://orcid.org/0009-0006-5669-9094"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Xie","raw_affiliation_strings":["Huawei TSC, Beijing, China. nicolas.xie@huawei.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei TSC, Beijing, China. nicolas.xie@huawei.com","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038736812","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0001-8861-7010"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Huawei TSC, Beijing, China. yanghao30@huawei.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei TSC, Beijing, China. yanghao30@huawei.com","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103085805","display_name":"Timothy Baldwin","orcid":"https://orcid.org/0000-0002-4445-1386"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE","AU"],"is_corresponding":true,"raw_author_name":"Timothy Baldwin","raw_affiliation_strings":["MBZUAI, Abu Dhabi, UAE. tb@ldwin.net","The University of Melbourne, Melbourne, Victoria, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI, Abu Dhabi, UAE. tb@ldwin.net","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"The University of Melbourne, Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067214173","display_name":"Karin Verspoor","orcid":"https://orcid.org/0000-0002-8661-1544"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Karin Verspoor","raw_affiliation_strings":["RMIT University, Melbourne, Victoria, Australia. karin.verspoor@rmit.edu.au","The University of Melbourne, Melbourne, Victoria, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Victoria, Australia. karin.verspoor@rmit.edu.au","institution_ids":["https://openalex.org/I82951845"]},{"raw_affiliation_string":"The University of Melbourne, Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006709668","https://openalex.org/A5038736812","https://openalex.org/A5067214173","https://openalex.org/A5100631225","https://openalex.org/A5101646797","https://openalex.org/A5103085805"],"corresponding_institution_ids":["https://openalex.org/I165779595","https://openalex.org/I2250955327","https://openalex.org/I4210113480","https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":0.3173,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62446941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"997","last_page":"1013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9976999759674072,"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/vagueness","display_name":"Vagueness","score":0.8094807863235474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7884187698364258},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6225512027740479},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5562496185302734},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5481123328208923},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5319752097129822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5108206272125244},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4970877468585968},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4585942327976227},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4439539909362793},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.42961305379867554},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4280139207839966},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3236643671989441},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10355997085571289},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.08174577355384827}],"concepts":[{"id":"https://openalex.org/C2776825360","wikidata":"https://www.wikidata.org/wiki/Q1411921","display_name":"Vagueness","level":3,"score":0.8094807863235474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884187698364258},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6225512027740479},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5562496185302734},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5481123328208923},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5319752097129822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5108206272125244},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4970877468585968},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4585942327976227},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4439539909362793},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.42961305379867554},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4280139207839966},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3236643671989441},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10355997085571289},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.08174577355384827},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00584","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00584","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00584/2154408/tacl_a_00584.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:102a2e07de3c4dfa8a9f9add5c4620d9","is_oa":true,"landing_page_url":"https://doaj.org/article/102a2e07de3c4dfa8a9f9add5c4620d9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 11 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00584","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00584","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00584/2154408/tacl_a_00584.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320974","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385859634.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W569594500","https://openalex.org/W1659833910","https://openalex.org/W1991656699","https://openalex.org/W2012798429","https://openalex.org/W2126400076","https://openalex.org/W2133458109","https://openalex.org/W2134168908","https://openalex.org/W2251869843","https://openalex.org/W2462305634","https://openalex.org/W2594908799","https://openalex.org/W2735784619","https://openalex.org/W2739351760","https://openalex.org/W2889272240","https://openalex.org/W2889968917","https://openalex.org/W2891555348","https://openalex.org/W2904008843","https://openalex.org/W2912323225","https://openalex.org/W2932893307","https://openalex.org/W2963341956","https://openalex.org/W2968573267","https://openalex.org/W2970641574","https://openalex.org/W2970752815","https://openalex.org/W2985347336","https://openalex.org/W3034906811","https://openalex.org/W3094834348","https://openalex.org/W3098467034","https://openalex.org/W3100806282","https://openalex.org/W3104033643","https://openalex.org/W3156636935","https://openalex.org/W3175655865","https://openalex.org/W3217467900","https://openalex.org/W4206636317","https://openalex.org/W4285228387","https://openalex.org/W4285298706","https://openalex.org/W4299585995","https://openalex.org/W4318618627","https://openalex.org/W4365211621","https://openalex.org/W4385567149","https://openalex.org/W4385573849","https://openalex.org/W6605913859","https://openalex.org/W6617145748","https://openalex.org/W6682338420","https://openalex.org/W6691695795","https://openalex.org/W6753143414","https://openalex.org/W6778883912","https://openalex.org/W6801805200","https://openalex.org/W7039744914"],"related_works":["https://openalex.org/W3078371441","https://openalex.org/W2116838603","https://openalex.org/W2766760871","https://openalex.org/W1997312918","https://openalex.org/W2047828095","https://openalex.org/W2365659184","https://openalex.org/W2359659532","https://openalex.org/W2380167751","https://openalex.org/W2617018490","https://openalex.org/W2390019325"],"abstract_inverted_index":{"Abstract":[0],"Despite":[1],"the":[2,28,44,48,58,104,116,120],"subjective":[3],"nature":[4],"of":[5,31,36,91],"semantic":[6,45],"textual":[7],"similarity":[8],"(STS)":[9],"and":[10,39,68],"pervasive":[11],"disagreements":[12],"in":[13,76],"STS":[14,61,100],"annotation,":[15],"existing":[16],"benchmarks":[17],"have":[18],"used":[19],"averaged":[20],"human":[21,32,74,108],"ratings":[22,50],"as":[23],"gold":[24],"standard.":[25],"Averaging":[26],"masks":[27],"true":[29],"distribution":[30],"opinions":[33,75],"on":[34,110],"examples":[35],"low":[37],"agreement,":[38],"prevents":[40],"models":[41,101],"from":[42],"capturing":[43],"vagueness":[46],"that":[47,80,98],"individual":[49,111],"represent.":[51],"In":[52],"this":[53],"work,":[54],"we":[55],"introduce":[56],"USTS,":[57],"first":[59],"Uncertainty-aware":[60],"dataset":[62],"with":[63],"\u223c15,000":[64],"Chinese":[65],"sentence":[66],"pairs":[67],"150,000":[69],"labels,":[70],"to":[71],"study":[72],"collective":[73],"STS.":[77],"Analysis":[78],"reveals":[79],"neither":[81],"a":[82,85,89],"scalar":[83],"nor":[84],"single":[86],"Gaussian":[87],"fits":[88],"set":[90],"observed":[92],"judgments":[93],"adequately.":[94],"We":[95],"further":[96],"show":[97],"current":[99],"cannot":[102],"capture":[103],"variance":[105],"caused":[106],"by":[107],"disagreement":[109],"instances,":[112],"but":[113],"rather":[114],"reflect":[115],"predictive":[117],"confidence":[118],"over":[119],"aggregate":[121],"dataset.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}