{"id":"https://openalex.org/W4309374880","doi":"https://doi.org/10.1109/smc53654.2022.9945218","title":"Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases","display_name":"Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases","publication_year":2022,"publication_date":"2022-10-09","ids":{"openalex":"https://openalex.org/W4309374880","doi":"https://doi.org/10.1109/smc53654.2022.9945218"},"language":"en","primary_location":{"id":"doi:10.1109/smc53654.2022.9945218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945218","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-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/A5037566627","display_name":"S\u0142awomir Dadas","orcid":"https://orcid.org/0000-0002-9177-6685"},"institutions":[{"id":"https://openalex.org/I4210139285","display_name":"National Information Processing Institute","ror":"https://ror.org/040fc1e14","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210139285"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Slawomir Dadas","raw_affiliation_strings":["National Information Processing Institute,Warsaw,Poland","National Information Processing Institute, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Information Processing Institute,Warsaw,Poland","institution_ids":["https://openalex.org/I4210139285"]},{"raw_affiliation_string":"National Information Processing Institute, Warsaw, Poland","institution_ids":["https://openalex.org/I4210139285"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5037566627"],"corresponding_institution_ids":["https://openalex.org/I4210139285"],"apc_list":null,"apc_paid":null,"fwci":0.2077,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.43201696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"371","last_page":"378"},"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":0.995199978351593,"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":0.8711549043655396},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.8085545301437378},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.741518497467041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6704300045967102},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6202768683433533},{"id":"https://openalex.org/keywords/paraphrase","display_name":"Paraphrase","score":0.5882080793380737},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5609111189842224},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4391445517539978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8711549043655396},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8085545301437378},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.741518497467041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6704300045967102},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6202768683433533},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.5882080793380737},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5609111189842224},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4391445517539978},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53654.2022.9945218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945218","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W630532510","https://openalex.org/W1614298861","https://openalex.org/W1840435438","https://openalex.org/W2064675550","https://openalex.org/W2131744502","https://openalex.org/W2250539671","https://openalex.org/W2250790822","https://openalex.org/W2419539795","https://openalex.org/W2493916176","https://openalex.org/W2611029872","https://openalex.org/W2739744877","https://openalex.org/W2752172973","https://openalex.org/W2786464815","https://openalex.org/W2790235966","https://openalex.org/W2794557536","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2963846996","https://openalex.org/W2963918774","https://openalex.org/W2964025273","https://openalex.org/W2964301648","https://openalex.org/W2965373594","https://openalex.org/W2970641574","https://openalex.org/W2973088264","https://openalex.org/W2982153178","https://openalex.org/W2990812481","https://openalex.org/W3038033387","https://openalex.org/W3097571385","https://openalex.org/W3100806282","https://openalex.org/W3122838366","https://openalex.org/W3156636935","https://openalex.org/W3157789198","https://openalex.org/W3175301726","https://openalex.org/W4246183800","https://openalex.org/W4294170691","https://openalex.org/W4299574851","https://openalex.org/W4385245566","https://openalex.org/W6629028937","https://openalex.org/W6636510571","https://openalex.org/W6679775712","https://openalex.org/W6682691769","https://openalex.org/W6691303741","https://openalex.org/W6717262007","https://openalex.org/W6736907568","https://openalex.org/W6739901393","https://openalex.org/W6743384090","https://openalex.org/W6748176785","https://openalex.org/W6748452836","https://openalex.org/W6749879876","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6766673545","https://openalex.org/W6769444473","https://openalex.org/W6779941907","https://openalex.org/W6789512599","https://openalex.org/W6794275021","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W1973985309","https://openalex.org/W3143920270","https://openalex.org/W2964212550","https://openalex.org/W2162507901","https://openalex.org/W2951718443","https://openalex.org/W4292355812","https://openalex.org/W2132019450","https://openalex.org/W2398825887","https://openalex.org/W2945702027","https://openalex.org/W3038033387"],"abstract_inverted_index":{"Sentence":[0],"embeddings":[1],"are":[2,16],"commonly":[3],"used":[4],"in":[5,121,149],"text":[6,95],"clustering":[7],"and":[8],"semantic":[9],"retrieval":[10],"tasks.":[11,140],"State-of-the-art":[12],"sentence":[13,29,75,116,158],"representation":[14],"methods":[15],"based":[17],"on":[18,23,126,134,145],"artificial":[19],"neural":[20],"networks":[21],"fine-tuned":[22],"large":[24],"collections":[25],"of":[26,33,89,138],"manually":[27,78],"labeled":[28,79],"pairs.":[30],"Sufficient":[31],"amount":[32],"annotated":[34],"data":[35,102],"is":[36,83],"available":[37,156],"for":[38,71],"high-resource":[39],"languages":[40],"such":[41],"as":[42],"English":[43],"or":[44],"Chinese.":[45],"In":[46,60],"less":[47,122],"popular":[48],"languages,":[49],"multilingual":[50,157],"models":[51],"have":[52],"to":[53,84,103],"be":[54,119],"used,":[55],"which":[56],"offer":[57],"lower":[58],"performance.":[59],"this":[61,65],"publication,":[62],"we":[63],"address":[64],"problem":[66],"by":[67],"proposing":[68],"a":[69,87,105,124,127,135],"method":[70,144],"training":[72],"effective":[73],"language-specific":[74],"encoders":[76],"without":[77],"data.":[80],"Our":[81,115],"approach":[82],"automatically":[85],"construct":[86],"dataset":[88],"paraphrase":[90],"pairs":[91],"from":[92],"sentence-aligned":[93],"bilingual":[94],"corpora.":[96],"We":[97,141],"then":[98],"use":[99],"the":[100,154],"collected":[101],"fine-tune":[104],"Transformer":[106],"language":[107],"model":[108],"with":[109,153],"an":[110],"additional":[111],"recurrent":[112],"pooling":[113],"layer.":[114],"encoder":[117],"can":[118],"trained":[120],"than":[123],"day":[125],"single":[128],"graphics":[129],"card,":[130],"achieving":[131],"high":[132],"performance":[133],"diverse":[136],"set":[137],"sentence-level":[139],"evaluate":[142],"our":[143],"eight":[146],"linguistic":[147],"tasks":[148],"Polish,":[150],"comparing":[151],"it":[152],"best":[155],"encoders.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}