{"id":"https://openalex.org/W3208395751","doi":"https://doi.org/10.48550/arxiv.2111.00157","title":"TransAug: Translate as Augmentation for Sentence Embeddings","display_name":"TransAug: Translate as Augmentation for Sentence Embeddings","publication_year":2021,"publication_date":"2021-10-30","ids":{"openalex":"https://openalex.org/W3208395751","doi":"https://doi.org/10.48550/arxiv.2111.00157","mag":"3208395751"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2111.00157","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.00157","pdf_url":"https://arxiv.org/pdf/2111.00157","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.00157","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100440609","display_name":"Jue Wang","orcid":"https://orcid.org/0000-0002-6712-1929","observed_orcids":["https://orcid.org/0000-0002-6712-1929"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Jue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100440609"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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":0.9976000189781189,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0007999999797903001,"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":0.00039999998989515007,"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/sentence-embeddings","display_name":"sentence embeddings","score":0.9929999709129333},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.8080000281333923},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.9449999928474426},{"id":"https://openalex.org/keywords/simcse","display_name":"SimCSE","score":0.7979999780654907},{"id":"https://openalex.org/keywords/semantic-textual-similarity","display_name":"semantic textual similarity","score":0.878000020980835},{"id":"https://openalex.org/keywords/two-stage-training","display_name":"two-stage training","score":0.5210000276565552},{"id":"https://openalex.org/keywords/multilingual-text-representation","display_name":"multilingual text representation","score":0.44200000166893005}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8396533727645874},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.796180009841919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825266122817993},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7068904042243958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6465510725975037},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4906364977359772},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4596317708492279},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3628695607185364},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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":"pmh:oai:arXiv.org:2111.00157","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.00157","pdf_url":"https://arxiv.org/pdf/2111.00157","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2111.00157","doi":"https://doi.org/10.48550/arxiv.2111.00157","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2111.00157","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.00157","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.00157","pdf_url":"https://arxiv.org/pdf/2111.00157","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W1555148682","https://openalex.org/W1614298861","https://openalex.org/W2014902591","https://openalex.org/W2028175314","https://openalex.org/W2114524997","https://openalex.org/W2126400076","https://openalex.org/W2131744502","https://openalex.org/W2133458109","https://openalex.org/W2138621090","https://openalex.org/W2152180407","https://openalex.org/W2160660844","https://openalex.org/W2163455955","https://openalex.org/W2250539671","https://openalex.org/W2250790822","https://openalex.org/W2251939518","https://openalex.org/W2462305634","https://openalex.org/W2481265265","https://openalex.org/W2488375705","https://openalex.org/W2607892599","https://openalex.org/W2768477045","https://openalex.org/W2912323225","https://openalex.org/W2914120296","https://openalex.org/W2953084091","https://openalex.org/W2963341956","https://openalex.org/W2964165804","https://openalex.org/W2965373594","https://openalex.org/W2965538726","https://openalex.org/W2971193649","https://openalex.org/W2981852735","https://openalex.org/W3009561768","https://openalex.org/W3035524453","https://openalex.org/W3038033387","https://openalex.org/W3039695075","https://openalex.org/W3104033643","https://openalex.org/W3105816068","https://openalex.org/W3118062200","https://openalex.org/W3122838366","https://openalex.org/W3126337491","https://openalex.org/W3135367836","https://openalex.org/W3156636935","https://openalex.org/W3173190788","https://openalex.org/W3194782062","https://openalex.org/W3201114717"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2375873920","https://openalex.org/W2384362569","https://openalex.org/W2146114872","https://openalex.org/W2142795561","https://openalex.org/W2392060890","https://openalex.org/W4205302943","https://openalex.org/W2392760275","https://openalex.org/W2561132942"],"abstract_inverted_index":{"While":[0],"contrastive":[1,106],"learning":[2,107],"greatly":[3],"advances":[4,52],"the":[5,15,18,33,53,101,110,132],"representation":[6],"of":[7,17,36,58],"sentence":[8,20,39,55],"embeddings,":[9],"it":[10],"is":[11],"still":[12],"limited":[13],"by":[14,142],"size":[16],"existing":[19],"datasets.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25,67,98],"present":[26],"TransAug":[27],"(Translate":[28],"as":[29,41,93],"Augmentation),":[30],"which":[31,89],"provide":[32],"first":[34,68],"exploration":[35],"utilizing":[37],"translated":[38],"pairs":[40],"data":[42,95],"augmentation":[43],"for":[44],"text,":[45],"and":[46,108,129,131],"introduce":[47],"a":[48,70,74,117],"two-stage":[49],"paradigm":[50],"to":[51],"state-of-the-art":[54],"embeddings.":[56],"Instead":[57],"adopting":[59],"an":[60],"encoder":[61,72,76,103],"trained":[62],"in":[63,78,86,135],"other":[64],"languages":[65],"setting,":[66],"distill":[69],"Chinese":[71,112],"from":[73],"SimCSE":[75,128],"(pretrained":[77],"English),":[79],"so":[80],"that":[81],"their":[82],"embeddings":[83],"are":[84],"close":[85],"semantic":[87,122],"space,":[88],"can":[90],"be":[91],"regraded":[92],"implicit":[94],"augmentation.":[96],"Then,":[97],"only":[99],"update":[100],"English":[102],"via":[104],"cross-lingual":[105],"frozen":[109],"distilled":[111],"encoder.":[113],"Our":[114],"approach":[115],"achieves":[116],"new":[118],"state-of-art":[119],"on":[120,138],"standard":[121],"textual":[123],"similarity":[124],"(STS),":[125],"outperforming":[126],"both":[127],"Sentence-T5,":[130],"best":[133],"performance":[134],"corresponding":[136],"tracks":[137],"transfer":[139],"tasks":[140],"evaluated":[141],"SentEval.":[143]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}