{"id":"https://openalex.org/W4412889892","doi":"https://doi.org/10.18653/v1/2025.acl-long.1299","title":"A Self-Denoising Model for Robust Few-Shot Relation Extraction","display_name":"A Self-Denoising Model for Robust Few-Shot Relation Extraction","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889892","doi":"https://doi.org/10.18653/v1/2025.acl-long.1299"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1299","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1299","pdf_url":"https://aclanthology.org/2025.acl-long.1299.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1299.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100358591","display_name":"Liang Zhang","orcid":"https://orcid.org/0000-0002-6317-0395"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117634646","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-9081-0802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101967248","display_name":"Ziyao Lu","orcid":"https://orcid.org/0000-0001-9176-6404"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyao Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024849044","display_name":"Fandong Meng","orcid":"https://orcid.org/0000-0002-8158-2377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fandong Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770462","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0002-2589-0164"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066326238","display_name":"Jinsong Su","orcid":"https://orcid.org/0000-0001-5606-7122"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinsong Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1844466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26782","last_page":"26797"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.816100001335144,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.816100001335144,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.657361626625061},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.597183108329773},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5808896422386169},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.518471896648407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46661797165870667},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.43800589442253113},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4215139150619507},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3652099072933197},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.19690901041030884},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11493858695030212},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.07856050133705139}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.657361626625061},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.597183108329773},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5808896422386169},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.518471896648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46661797165870667},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.43800589442253113},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4215139150619507},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3652099072933197},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.19690901041030884},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11493858695030212},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.07856050133705139},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1299","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1299","pdf_url":"https://aclanthology.org/2025.acl-long.1299.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1299","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1299","pdf_url":"https://aclanthology.org/2025.acl-long.1299.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2814589030","display_name":null,"funder_award_id":"3502Z20231043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8535310050","display_name":null,"funder_award_id":"62276219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889892.pdf","grobid_xml":"https://content.openalex.org/works/W4412889892.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W4411535265","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966"],"abstract_inverted_index":{"The":[0],"few-shot":[1],"relation":[2,145],"extraction":[3],"(FSRE)":[4],"aims":[5],"at":[6],"enhancing":[7,91],"the":[8,30,34,68,77,92,134,139,160,193],"model's":[9],"generalization":[10],"to":[11,36,73,104,125,150,179],"new":[12,37,156],"relations":[13,157],"with":[14],"a":[15,63,98,119,144,168],"few":[16],"labeled":[17,42],"instances.Existing":[18],"studies":[19],"usually":[20],"adopt":[21],"prototype":[22],"networks":[23],"(Pro-toNets)":[24],"for":[25,90,101,155],"FSRE":[26,93],"and":[27,142,177],"assume":[28],"that":[29,66,82],"support":[31,43,78,86,112,130,185],"set,":[32],"adapting":[33],"model":[35,94,100,106,205],"relations,":[38],"only":[39],"contains":[40],"accurately":[41],"instances.However,":[44],"this":[45,58],"assumption":[46],"is":[47,88],"often":[48],"unrealistic,":[49],"as":[50],"even":[51,198],"carefully-annotated":[52],"datasets":[53,191],"commonly":[54],"contain":[55],"mislabeled":[56,85,111],"instances.In":[57],"paper,":[59],"we":[60,80,96,166],"first":[61],"conduct":[62],"preliminary":[64],"study":[65],"reveals":[67],"high":[69],"sensitivity":[70],"of":[71,129,195],"ProtoNets":[72],"noisy":[74,127,182,202],"labels":[75,128,162,183],"in":[76,138,184,199],"set.Moreover,":[79],"find":[81],"fully":[83],"leveraging":[84],"instances":[87,131],"crucial":[89],"robustness.Thus,":[95],"propose":[97,167],"self-denoising":[99],"FSRE,":[102],"designed":[103],"improve":[105],"robustness":[107,194],"by":[108,164],"automatically":[109],"correcting":[110],"instances.It":[113],"comprises":[114],"two":[115,189],"core":[116],"components:":[117],"1)":[118],"label":[120],"correction":[121],"module":[122,147],"(LCM),":[123],"used":[124],"correct":[126],"based":[132,158],"on":[133,159,174,188],"distances":[135],"between":[136],"them":[137],"embedding":[140],"space,":[141],"2)":[143],"classification":[146],"(RCM),":[148],"aimed":[149],"achieve":[151],"more":[152],"accurate":[153],"predictions":[154],"corrected":[161],"produced":[163],"LCM.Moreover,":[165],"feedback-based":[169],"training":[170,175],"strategy,":[171],"which":[172],"focuses":[173],"LCM":[176],"RCM":[178],"synergistically":[180],"handle":[181],"set.Experimental":[186],"results":[187],"public":[190],"confirm":[192],"our":[196,204],"model.Particularly,":[197],"scenarios":[200],"without":[201],"labels,":[203],"significantly":[206],"outperforms":[207],"all":[208],"baselines.":[209]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}