{"id":"https://openalex.org/W2942911521","doi":"https://doi.org/10.1093/llc/fqy076","title":"Linguistic analysis of datasets for semantic textual similarity","display_name":"Linguistic analysis of datasets for semantic textual similarity","publication_year":2019,"publication_date":"2019-01-17","ids":{"openalex":"https://openalex.org/W2942911521","doi":"https://doi.org/10.1093/llc/fqy076","mag":"2942911521"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqy076","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqy076","pdf_url":null,"source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"},"type":"article","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/A5100683869","display_name":"Chunlin Wang","orcid":"https://orcid.org/0000-0003-4675-1355"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chunlin Wang","raw_affiliation_strings":["Artificial Solutions Iberia S.L., Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Solutions Iberia S.L., Barcelona","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077165478","display_name":"Irene Castell\u00f3n Masalles","orcid":"https://orcid.org/0000-0003-4184-9652"},"institutions":[{"id":"https://openalex.org/I71999127","display_name":"Universitat de Barcelona","ror":"https://ror.org/021018s57","country_code":"ES","type":"education","lineage":["https://openalex.org/I71999127"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Irene Castell\u00f3n","raw_affiliation_strings":["Departamento de Filolog\u00eda Catalana y Ling\u00fc\u00edstica General, Universidad de Barcelona, Gran Via de les Corts Catalanes, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Filolog\u00eda Catalana y Ling\u00fc\u00edstica General, Universidad de Barcelona, Gran Via de les Corts Catalanes, Barcelona","institution_ids":["https://openalex.org/I71999127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057739549","display_name":"Elisabet Comelles","orcid":"https://orcid.org/0000-0002-4753-2712"},"institutions":[{"id":"https://openalex.org/I71999127","display_name":"Universitat de Barcelona","ror":"https://ror.org/021018s57","country_code":"ES","type":"education","lineage":["https://openalex.org/I71999127"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Elisabet Comelles","raw_affiliation_strings":["Departamento de Lenguas y Literaturas Modernas y de Estudios Ingleses, Universidad de Barcelona, Gran Via de les Corts Catalanes, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Lenguas y Literaturas Modernas y de Estudios Ingleses, Universidad de Barcelona, Gran Via de les Corts Catalanes, Barcelona","institution_ids":["https://openalex.org/I71999127"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100683869"],"corresponding_institution_ids":[],"apc_list":{"value":2522,"currency":"GBP","value_usd":3093},"apc_paid":null,"fwci":0.1451,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55956817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"35","issue":"2","first_page":"471","last_page":"484"},"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":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/T13629","display_name":"Text Readability and Simplification","score":0.9947999715805054,"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/natural-language-processing","display_name":"Natural language processing","score":0.7582615613937378},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7316246628761292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6671072244644165},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.625205934047699},{"id":"https://openalex.org/keywords/semeval","display_name":"SemEval","score":0.6217968463897705},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5854460597038269},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5757140517234802},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5650231242179871},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.5516440272331238},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5498433709144592},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5134890675544739},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5029959082603455},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4686305522918701},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4297493100166321},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.42317262291908264},{"id":"https://openalex.org/keywords/deep-linguistic-processing","display_name":"Deep linguistic processing","score":0.4104998707771301}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7582615613937378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7316246628761292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6671072244644165},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.625205934047699},{"id":"https://openalex.org/C44572571","wikidata":"https://www.wikidata.org/wiki/Q7448970","display_name":"SemEval","level":3,"score":0.6217968463897705},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5854460597038269},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5757140517234802},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5650231242179871},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.5516440272331238},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5498433709144592},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5134890675544739},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5029959082603455},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4686305522918701},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4297493100166321},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.42317262291908264},{"id":"https://openalex.org/C64249296","wikidata":"https://www.wikidata.org/wiki/Q5250411","display_name":"Deep linguistic processing","level":2,"score":0.4104998707771301},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/llc/fqy076","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqy076","pdf_url":null,"source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W173617392","https://openalex.org/W806995027","https://openalex.org/W1504725289","https://openalex.org/W1983578042","https://openalex.org/W2038721957","https://openalex.org/W2126400076","https://openalex.org/W2130158090","https://openalex.org/W2147192413","https://openalex.org/W2165979181","https://openalex.org/W2272153972","https://openalex.org/W2615753704","https://openalex.org/W2740887992","https://openalex.org/W2750811310","https://openalex.org/W2781528640","https://openalex.org/W2799915114","https://openalex.org/W2912323225","https://openalex.org/W2913332048","https://openalex.org/W2915300452","https://openalex.org/W4235505822","https://openalex.org/W6684589840"],"related_works":["https://openalex.org/W1988325893","https://openalex.org/W3029012650","https://openalex.org/W2752041471","https://openalex.org/W78638240","https://openalex.org/W2252122760","https://openalex.org/W2105461184","https://openalex.org/W2103835134","https://openalex.org/W4238802473","https://openalex.org/W2034503175","https://openalex.org/W2036755558"],"abstract_inverted_index":{"Abstract":[0],"Semantic":[1,36],"Textual":[2],"Similarity":[3],"(STS),":[4],"which":[5],"measures":[6],"the":[7,31,35,58,75,94,108,115,118,130],"equivalence":[8],"of":[9,110,117],"meanings":[10],"between":[11,102],"two":[12],"textual":[13],"segments,":[14],"is":[15],"an":[16],"important":[17],"and":[18,69,100,144],"useful":[19,138],"task":[20,43],"in":[21,44,97,129],"Natural":[22],"Language":[23],"Processing.":[24],"In":[25],"this":[26,42],"article,":[27],"we":[28,105],"have":[29,73,85],"analyzed":[30],"datasets":[32],"provided":[33],"by":[34],"Evaluation":[37],"(SemEval)":[38],"2012\u20132014":[39],"campaigns":[40],"for":[41,52,125,140],"order":[45],"to":[46,93,114],"find":[47],"out":[48],"appropriate":[49],"linguistic":[50,61,82,111,145],"features":[51,62,112],"each":[53],"dataset,":[54],"taking":[55],"into":[56],"account":[57],"influence":[59],"that":[60,80,107],"at":[63],"different":[64,87,90],"levels":[65],"(e.g.":[66],"syntactic":[67],"constituents":[68],"lexical":[70],"semantics)":[71],"might":[72,120],"on":[74,89],"sentence":[76,98],"similarity.":[77],"Results":[78],"indicate":[79],"a":[81,86,122,137],"feature":[83,146],"may":[84],"effect":[88],"corpus":[91],"due":[92],"great":[95],"difference":[96],"structure":[99],"vocabulary":[101],"datasets.":[103],"Thus,":[104],"conclude":[106],"selection":[109],"according":[113],"genre":[116],"text":[119],"be":[121,136],"good":[123],"strategy":[124],"obtaining":[126],"better":[127],"results":[128],"STS":[131],"task.":[132],"This":[133],"analysis":[134],"could":[135],"reference":[139],"measuring":[141],"system":[142],"building":[143],"tuning.":[147]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
