{"id":"https://openalex.org/W4327598424","doi":"https://doi.org/10.1017/s1351324923000086","title":"Towards diverse and contextually anchored paraphrase modeling: A dataset and baselines for Finnish","display_name":"Towards diverse and contextually anchored paraphrase modeling: A dataset and baselines for Finnish","publication_year":2023,"publication_date":"2023-03-16","ids":{"openalex":"https://openalex.org/W4327598424","doi":"https://doi.org/10.1017/s1351324923000086"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324923000086","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000086","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/540F08D91022FE4221476D4FBFB9417C/S1351324923000086a.pdf/div-class-title-towards-diverse-and-contextually-anchored-paraphrase-modeling-a-dataset-and-baselines-for-finnish-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/540F08D91022FE4221476D4FBFB9417C/S1351324923000086a.pdf/div-class-title-towards-diverse-and-contextually-anchored-paraphrase-modeling-a-dataset-and-baselines-for-finnish-div.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048932608","display_name":"Jenna Kanerva","orcid":"https://orcid.org/0000-0003-4580-5366"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Jenna Kanerva","raw_affiliation_strings":["TurkuNLP, Department of Computing, University of Turku, Turku, Finland","Department of Computing, University of Turku, Turku, Finland"],"raw_orcid":"https://orcid.org/0000-0003-4580-5366","affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019929457","display_name":"Filip Ginter","orcid":"https://orcid.org/0000-0002-5484-6103"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Filip Ginter","raw_affiliation_strings":["TurkuNLP, Department of Computing, University of Turku, Turku, Finland","Department of Computing, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005278427","display_name":"Li-Hsin Chang","orcid":"https://orcid.org/0000-0002-1301-2823"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Li-Hsin Chang","raw_affiliation_strings":["TurkuNLP, Department of Computing, University of Turku, Turku, Finland","Department of Computing, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005267278","display_name":"Iiro Rastas","orcid":null},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Iiro Rastas","raw_affiliation_strings":["TurkuNLP, Department of Computing, University of Turku, Turku, Finland","Department of Computing, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066222419","display_name":"Valtteri Skantsi","orcid":"https://orcid.org/0000-0002-1230-9983"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Valtteri Skantsi","raw_affiliation_strings":["TurkuNLP, Department of Computing, University of Turku, Turku, Finland","Department of Computing, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020795562","display_name":"Jemina Kilpel\u00e4inen","orcid":null},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jemina Kilpel\u00e4inen","raw_affiliation_strings":["TurkuNLP, Department of Computing, University of Turku, Turku, Finland","Department of Computing, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046560199","display_name":"Hanna-Mari Kupari","orcid":"https://orcid.org/0000-0003-2515-5861"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Hanna-Mari Kupari","raw_affiliation_strings":["TurkuNLP, Department of Computing, University of Turku, Turku, Finland","Department of Computing, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023279646","display_name":"Aurora Piirto","orcid":null},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Aurora Piirto","raw_affiliation_strings":["TurkuNLP, Department of Computing, University of Turku, Turku, Finland","Department of Computing, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063331608","display_name":"Jenna Saarni","orcid":"https://orcid.org/0000-0003-4363-4911"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jenna Saarni","raw_affiliation_strings":["TurkuNLP, Department of Computing, University of Turku, Turku, Finland","Department of Computing, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033472585","display_name":"Maija Sev\u00f3n","orcid":null},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Maija Sev\u00f3n","raw_affiliation_strings":["TurkuNLP, Department of Computing, University of Turku, Turku, Finland","Department of Computing, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071777069","display_name":"Otto Tarkka","orcid":"https://orcid.org/0000-0001-8200-0319"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Otto Tarkka","raw_affiliation_strings":["TurkuNLP, Department of Computing, University of Turku, Turku, Finland","Department of Computing, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5048932608"],"corresponding_institution_ids":["https://openalex.org/I155660961"],"apc_list":null,"apc_paid":null,"fwci":0.4759,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66860936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"30","issue":"2","first_page":"319","last_page":"353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/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":0.993399977684021,"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/paraphrase","display_name":"Paraphrase","score":0.9880059957504272},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7749593257904053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.766636073589325},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6965766549110413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6892012357711792},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5242878794670105},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.43820852041244507},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.43348395824432373},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3604591488838196},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.08068135380744934}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.9880059957504272},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7749593257904053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766636073589325},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6965766549110413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6892012357711792},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5242878794670105},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.43820852041244507},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.43348395824432373},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3604591488838196},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.08068135380744934},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s1351324923000086","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000086","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/540F08D91022FE4221476D4FBFB9417C/S1351324923000086a.pdf/div-class-title-towards-diverse-and-contextually-anchored-paraphrase-modeling-a-dataset-and-baselines-for-finnish-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:www.utupub.fi:10024/184424","is_oa":true,"landing_page_url":"https://www.utupub.fi/handle/10024/184424","pdf_url":"https://www.utupub.fi/bitstream/10024/184424/1/towards-diverse-and-contextually-anchored-paraphrase-modeling-a-dataset-and-baselines-for-finnish.pdf","source":{"id":"https://openalex.org/S4306402470","display_name":"UTUPub (University of Turku)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I155660961","host_organization_name":"University of Turku","host_organization_lineage":["https://openalex.org/I155660961"],"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":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1017/s1351324923000086","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000086","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/540F08D91022FE4221476D4FBFB9417C/S1351324923000086a.pdf/div-class-title-towards-diverse-and-contextually-anchored-paraphrase-modeling-a-dataset-and-baselines-for-finnish-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"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/W4327598424.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W2016172157","https://openalex.org/W2250818554","https://openalex.org/W2398064412","https://openalex.org/W2768116540","https://openalex.org/W2789824124","https://openalex.org/W2886198413","https://openalex.org/W2896457183","https://openalex.org/W2945576070","https://openalex.org/W2963508788","https://openalex.org/W2963672008","https://openalex.org/W2964212550","https://openalex.org/W2970641033","https://openalex.org/W2970641574","https://openalex.org/W2985347336","https://openalex.org/W2987395887","https://openalex.org/W2998702515","https://openalex.org/W3032819430","https://openalex.org/W3035390927","https://openalex.org/W3045669807","https://openalex.org/W3092854299","https://openalex.org/W3102773004","https://openalex.org/W3153128515","https://openalex.org/W3157059448","https://openalex.org/W3195775898","https://openalex.org/W3206428286","https://openalex.org/W4212774754","https://openalex.org/W6691444529","https://openalex.org/W6691478284","https://openalex.org/W6691552196","https://openalex.org/W6751633227","https://openalex.org/W6762917398","https://openalex.org/W6791595262","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W3195775898","https://openalex.org/W4287024084","https://openalex.org/W4321512656","https://openalex.org/W2978707643","https://openalex.org/W2294233724","https://openalex.org/W4378713476","https://openalex.org/W2169813772","https://openalex.org/W2736149021","https://openalex.org/W2007563177","https://openalex.org/W4248451614"],"abstract_inverted_index":{"Abstract":[0],"In":[1,112,166],"this":[2,69,170,194],"paper,":[3],"we":[4,71],"study":[5,187,212],"natural":[6,37],"language":[7],"paraphrasing":[8,188],"from":[9,137,161],"both":[10],"corpus":[11,83,89,199,245],"creation":[12],"and":[13,122,152,217],"modeling":[14],"points":[15],"of":[16,29,32,84,96,118,232,277],"view.":[17],"We":[18,210],"focus":[19],"in":[20,35,56,86,128,189,243,282],"particular":[21],"on":[22,219,259,266,287],"the":[23,27,49,73,77,116,119,132,176,196,202,207,220,233,238,244,247,257,271,278,283,288,303,308],"methodology":[24],"that":[25],"allows":[26,143,172],"extraction":[28],"challenging":[30,148,230],"examples":[31],"paraphrase":[33,94,120,198,214,225,263,289],"pairs":[34,121,279],"their":[36,109],"textual":[38],"context,":[39,58],"leading":[40],"to":[41,52,101,114,145,168,174,186],"a":[42,147,229,260],"dataset":[43,149,234],"potentially":[44],"more":[45,153],"suitable":[46],"for":[47,180,206],"evaluating":[48,256],"models\u2019":[50],"ability":[51],"represent":[53],"meaning,":[54],"especially":[55],"document":[57,178,204],"when":[59,235,255],"compared":[60],"with":[61],"those":[62,162],"gathered":[63],"using":[64,237],"various":[65],"sentence-level":[66],"heuristics.":[67,165],"To":[68,191],"end,":[70],"introduce":[72],"Turku":[74,292],"Paraphrase":[75,293],"Corpus,":[76],"first":[78,197],"large-scale,":[79],"fully":[80],"manually":[81,92,135],"annotated":[82,208],"paraphrases":[85,133,156],"Finnish.":[87],"The":[88,291],"contains":[90],"104,645":[91],"labeled":[93],"pairs,":[95],"which":[97,200],"98%":[98],"are":[99,134,273],"verified":[100],"be":[102,159],"true":[103],"paraphrases,":[104],"either":[105],"universally":[106],"or":[107],"within":[108],"present":[110],"context.":[111,190],"order":[113],"control":[115],"diversity":[117],"avoid":[123],"certain":[124],"biases":[125],"easily":[126],"introduced":[127],"automatic":[129],"candidate":[130,269],"extraction,":[131],"collected":[136,163],"different":[138],"paraphrase-rich":[139],"text":[140],"sources.":[141],"This":[142],"us":[144,173],"create":[146],"including":[150],"longer":[151],"lexically":[154],"diverse":[155],"than":[157],"can":[158],"expected":[160],"through":[164,302],"addition":[167],"quality,":[169],"also":[171,211],"keep":[175],"original":[177,203],"context":[179,205],"each":[181],"pair,":[182],"making":[183],"it":[184],"possible":[185],"our":[192],"knowledge,":[193],"is":[195,295],"provides":[201],"pairs.":[209],"several":[213],"models":[215,258],"trained":[216],"evaluated":[218],"new":[221],"data.":[222],"Our":[223],"initial":[224],"classification":[226],"experiments":[227],"indicate":[228],"nature":[231],"classifying":[236],"detailed":[239],"labeling":[240],"scheme":[241],"used":[242],"annotation,":[246],"accuracy":[248],"substantially":[249],"lacking":[250],"behind":[251],"human":[252],"performance.":[253],"However,":[254],"large":[261],"scale":[262],"retrieval":[264],"task":[265],"almost":[267],"400M":[268],"sentences,":[270],"results":[272],"highly":[274],"encouraging,":[275],"29\u201353%":[276],"being":[280],"ranked":[281],"top":[284],"10":[285],"depending":[286],"type.":[290],"Corpus":[294],"available":[296],"at":[297],"github.com/TurkuNLP/Turku-paraphrase-corpus":[298],"as":[299,301],"well":[300],"popular":[304],"HuggingFace":[305],"datasets":[306],"under":[307],"CC-BY-SA":[309],"license.":[310]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
