{"id":"https://openalex.org/W2950235146","doi":"https://doi.org/10.18653/v1/p19-1268","title":"Aiming beyond the Obvious: Identifying Non-Obvious Cases in Semantic Similarity Datasets","display_name":"Aiming beyond the Obvious: Identifying Non-Obvious Cases in Semantic Similarity Datasets","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2950235146","doi":"https://doi.org/10.18653/v1/p19-1268","mag":"2950235146"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1268","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1268","pdf_url":"https://www.aclweb.org/anthology/P19-1268.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1268.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056189765","display_name":"Nicole Peinelt","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]},{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Nicole Peinelt","raw_affiliation_strings":["The Alan Turing Institute, London, UK","University of Warwick, Coventry, UK"],"affiliations":[{"raw_affiliation_string":"The Alan Turing Institute, London, UK","institution_ids":["https://openalex.org/I4210128584"]},{"raw_affiliation_string":"University of Warwick, Coventry, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007426895","display_name":"Maria Liakata","orcid":"https://orcid.org/0000-0001-5765-0416"},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]},{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maria Liakata","raw_affiliation_strings":["The Alan Turing Institute, London, UK","University of Warwick, Coventry, UK"],"affiliations":[{"raw_affiliation_string":"The Alan Turing Institute, London, UK","institution_ids":["https://openalex.org/I4210128584"]},{"raw_affiliation_string":"University of Warwick, Coventry, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004209770","display_name":"Dong Nguyen","orcid":"https://orcid.org/0000-0002-6062-3117"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB","NL"],"is_corresponding":false,"raw_author_name":"Dong Nguyen","raw_affiliation_strings":["The Alan Turing Institute, London, UK","Utrecht University, Utrecht, The Netherlands"],"affiliations":[{"raw_affiliation_string":"The Alan Turing Institute, London, UK","institution_ids":["https://openalex.org/I4210128584"]},{"raw_affiliation_string":"Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056189765"],"corresponding_institution_ids":["https://openalex.org/I39555362","https://openalex.org/I4210128584"],"apc_list":null,"apc_paid":null,"fwci":1.1561,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84145753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2792","last_page":"2798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9968000054359436,"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":0.9789000153541565,"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/computer-science","display_name":"Computer science","score":0.7132545113563538},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6725587844848633},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5964969396591187},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47945013642311096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41300034523010254},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3630254864692688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132545113563538},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6725587844848633},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5964969396591187},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47945013642311096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41300034523010254},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3630254864692688},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p19-1268","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1268","pdf_url":"https://www.aclweb.org/anthology/P19-1268.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:uu:oai:dspace.library.uu.nl:1874/389909","is_oa":false,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/389909","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2792. Association for Computational Linguistics","raw_type":"info:eu-repo/semantics/bookpart"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1268","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1268","pdf_url":"https://www.aclweb.org/anthology/P19-1268.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1223493200","display_name":null,"funder_award_id":"EP/N510129/1.","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1309768829","display_name":null,"funder_award_id":"EP/N510129/1.","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G1633672591","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3855435662","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G4072067573","display_name":null,"funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G444630160","display_name":null,"funder_award_id":"EP/N510129/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4500485203","display_name":"The Alan Turing Institute","funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G777199097","display_name":null,"funder_award_id":"EPSRC grant EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320313467","display_name":"Alan Turing Institute","ror":"https://ror.org/035dkdb55"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950235146.pdf","grobid_xml":"https://content.openalex.org/works/W2950235146.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W2103305545","https://openalex.org/W2146950091","https://openalex.org/W2251427843","https://openalex.org/W2252217313","https://openalex.org/W2306229986","https://openalex.org/W2468484304","https://openalex.org/W2593833795","https://openalex.org/W2612867916","https://openalex.org/W2739599645","https://openalex.org/W2806885203","https://openalex.org/W2962727366","https://openalex.org/W2962736243","https://openalex.org/W2963323070","https://openalex.org/W2963341493","https://openalex.org/W2963412182","https://openalex.org/W3104033643"],"related_works":["https://openalex.org/W2114797768","https://openalex.org/W4376653378","https://openalex.org/W2380654781","https://openalex.org/W3204019825","https://openalex.org/W2176214140","https://openalex.org/W2516873349","https://openalex.org/W2898077673","https://openalex.org/W4385239468","https://openalex.org/W1990601549","https://openalex.org/W2022470916"],"abstract_inverted_index":{"Existing":[0],"datasets":[1,43],"for":[2,84,87],"scoring":[3],"text":[4,30],"pairs":[5,31],"in":[6,44],"terms":[7,45],"of":[8,20,46,62,71],"semantic":[9,63,88],"similarity":[10,72],"contain":[11],"instances":[12],"whose":[13],"resolution":[14],"differs":[15],"according":[16],"to":[17,25,57],"the":[18,59],"degree":[19],"difficulty.":[21],"This":[22],"paper":[23],"proposes":[24],"distinguish":[26],"obvious":[27],"from":[28],"non-obvious":[29,60],"based":[32],"on":[33],"superficial":[34],"lexical":[35],"overlap":[36],"and":[37,50,78],"ground-truth":[38],"labels.":[39],"We":[40,65],"characterise":[41],"existing":[42],"containing":[47],"difficult":[48],"cases":[49,61,70],"find":[51],"that":[52,68,80],"recently":[53],"proposed":[54],"models":[55],"struggle":[56],"capture":[58],"similarity.":[64,89],"describe":[66],"metrics":[67],"emphasise":[69],"which":[73],"require":[74],"more":[75],"complex":[76],"inference":[77],"propose":[79],"these":[81],"are":[82],"used":[83],"evaluating":[85],"systems":[86]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}