{"id":"https://openalex.org/W4226307002","doi":"https://doi.org/10.1007/s10579-023-09715-7","title":"Semantic search as extractive paraphrase span detection","display_name":"Semantic search as extractive paraphrase span detection","publication_year":2024,"publication_date":"2024-02-01","ids":{"openalex":"https://openalex.org/W4226307002","doi":"https://doi.org/10.1007/s10579-023-09715-7"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-023-09715-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-023-09715-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-023-09715-7.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-023-09715-7.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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073565606","display_name":"Hanna Kitti","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":"Hanna Kitti","raw_affiliation_strings":["TurkuNLP, 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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102487703","display_name":"Li\u2010Hsin Chang","orcid":"https://orcid.org/0009-0000-1534-7224"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053401029","display_name":"Teemu Vahtola","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Teemu Vahtola","raw_affiliation_strings":["Department of Digital Humanities, Faculty of Arts, University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Digital Humanities, Faculty of Arts, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061159001","display_name":"Mathias Creutz","orcid":"https://orcid.org/0000-0003-1862-4172"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mathias Creutz","raw_affiliation_strings":["Department of Digital Humanities, Faculty of Arts, University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Digital Humanities, Faculty of Arts, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TurkuNLP, Department of Computing, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048932608"],"corresponding_institution_ids":["https://openalex.org/I155660961"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00179445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"59","issue":"1","first_page":"257","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991000294685364,"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":0.9879999756813049,"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":0.9853384494781494},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7891624569892883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7736546993255615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.691536009311676},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.642181396484375},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5211167931556702},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4975445568561554},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46602627635002136},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45117443799972534},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4368857443332672},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4358886182308197},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.432489812374115},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.4168583154678345},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4168393015861511}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.9853384494781494},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7891624569892883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736546993255615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.691536009311676},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.642181396484375},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5211167931556702},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4975445568561554},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46602627635002136},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45117443799972534},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4368857443332672},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4358886182308197},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.432489812374115},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4168583154678345},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4168393015861511},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10579-023-09715-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-023-09715-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-023-09715-7.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2112.04886","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.04886","pdf_url":"https://arxiv.org/pdf/2112.04886","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2112.04886","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2112.04886","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1007/s10579-023-09715-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-023-09715-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-023-09715-7.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G6476763384","display_name":"European Language Grid","funder_award_id":"825627","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320323313","display_name":"Turun Yliopisto","ror":"https://ror.org/05vghhr25"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4226307002.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W2462305634","https://openalex.org/W2739351760","https://openalex.org/W2788277448","https://openalex.org/W2962985038","https://openalex.org/W2963216553","https://openalex.org/W2963323070","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W2966838849","https://openalex.org/W2970641574","https://openalex.org/W2979826702","https://openalex.org/W2981852735","https://openalex.org/W3023958260","https://openalex.org/W3034469191","https://openalex.org/W3045462440","https://openalex.org/W3045958725","https://openalex.org/W3082928416","https://openalex.org/W3095789240","https://openalex.org/W3102773004","https://openalex.org/W3157059448","https://openalex.org/W3168875417","https://openalex.org/W3194222855","https://openalex.org/W3195775898","https://openalex.org/W4327598424"],"related_works":["https://openalex.org/W149980","https://openalex.org/W881173","https://openalex.org/W505434","https://openalex.org/W8895266","https://openalex.org/W14808","https://openalex.org/W745926","https://openalex.org/W1788602","https://openalex.org/W8411197","https://openalex.org/W2060686","https://openalex.org/W13206174"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"this":[2],"paper,":[3],"we":[4,95,216],"approach":[5,67,109],"the":[6,29,40,63,79,149,163,172,185,192,198,237],"problem":[7],"of":[8,15,23,75,83,103,132,139,147,154,208],"semantic":[9],"search":[10],"by":[11,98,126,201],"introducing":[12],"a":[13,21,26,37,69,73,144,218],"task":[14,30],"paraphrase":[16,35,88,106,150,223,233],"span":[17,65,107,155,193,238],"detection,":[18],"i.e.":[19],"given":[20,38],"segment":[22,74],"text":[24],"as":[25,44,118,120],"query":[27],"phrase,":[28],"is":[31],"to":[32,71,178,187],"identify":[33],"its":[34],"in":[36,47,54,130,137,152,206],"document,":[39],"same":[41],"modelling":[42,148],"setup":[43],"typically":[45],"used":[46,160],"extractive":[48],"question":[49],"answering.":[50],"While":[51],"current":[52],"work":[53],"paraphrasing":[55],"has":[56],"almost":[57,212],"uniquely":[58],"focused":[59],"on":[60],"sentence-level":[61,113,164,188,199],"approaches,":[62],"novel":[64],"detection":[66,108,194,239],"gives":[68],"possibility":[70],"retrieve":[72],"arbitrary":[76],"length.":[77],"On":[78],"Turku":[80],"Paraphrase":[81],"Corpus":[82],"100,000":[84],"manually":[85,231],"extracted":[86],"Finnish":[87],"pairs":[89],"including":[90],"their":[91],"original":[92],"document":[93],"context,":[94],"find":[96],"that":[97],"achieving":[99],"an":[100],"exact":[101,133,209],"match":[102],"88.73":[104],"our":[105],"outperforms":[110,197],"widely":[111],"adopted":[112],"retrieval":[114,151,173,189],"baselines":[115,200],"(lexical":[116],"similarity":[117],"well":[119],"BERT":[121],"and":[122,135,211],"SBERT":[123],"sentence":[124,161],"embeddings)":[125],"more":[127,202],"than":[128,158,203],"20pp":[129],"terms":[131,138,153,207],"match,":[134,210],"11pp":[136],"token-level":[140],"F-score.":[141,214],"This":[142],"demonstrates":[143],"strong":[145],"advantage":[146],"extraction":[156],"rather":[157],"commonly":[159],"similarity,":[162],"approaches":[165],"being":[166],"clearly":[167],"suboptimal":[168],"for":[169,220,228,235],"applications":[170],"where":[171,230],"targets":[174,190],"are":[175,241],"not":[176,242],"guaranteed":[177],"be":[179],"full":[180],"sentences.":[181],"Even":[182],"when":[183],"limiting":[184],"evaluation":[186],"only,":[191],"model":[195,240],"still":[196],"4":[204],"pp":[205],"6pp":[213],"Additionally,":[215],"introduce":[217],"method":[219],"creating":[221],"artificial":[222],"data":[224],"through":[225],"back-translation,":[226],"suitable":[227],"languages":[229],"annotated":[232],"resources":[234],"training":[236],"available.":[243]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2022-05-05T00:00:00"}
