{"id":"https://openalex.org/W3210658007","doi":"https://doi.org/10.1145/3459637.3482268","title":"Learning Discriminative and Unbiased Representations for Few-Shot Relation Extraction","display_name":"Learning Discriminative and Unbiased Representations for Few-Shot Relation Extraction","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3210658007","doi":"https://doi.org/10.1145/3459637.3482268","mag":"3210658007"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","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/A5011412438","display_name":"Jiale Han","orcid":"https://orcid.org/0000-0001-6477-0424"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiale Han","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100640942","display_name":"Bo Cheng","orcid":"https://orcid.org/0000-0003-2160-2839"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Cheng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020360628","display_name":"Guoshun Nan","orcid":"https://orcid.org/0000-0002-1987-2736"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guoshun Nan","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011412438"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":1.3597,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84804518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"638","last_page":"648"},"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":0.9968000054359436,"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":0.996399998664856,"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/discriminative-model","display_name":"Discriminative model","score":0.875615119934082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7460986971855164},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7171662449836731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6487514972686768},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6043891310691833},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5278877019882202},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5216201543807983},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5117868781089783},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.480726033449173},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4551418423652649},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4457733929157257},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.44061288237571716},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4306504726409912},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.41587409377098083},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1503589153289795},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.12205183506011963},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1183619499206543}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.875615119934082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460986971855164},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7171662449836731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6487514972686768},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6043891310691833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5278877019882202},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5216201543807983},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5117868781089783},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.480726033449173},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4551418423652649},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4457733929157257},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44061288237571716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4306504726409912},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.41587409377098083},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1503589153289795},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.12205183506011963},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1183619499206543},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459637.3482268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G2096905388","display_name":null,"funder_award_id":"61972043, 61772479","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5132779740","display_name":null,"funder_award_id":"2018YFB1003804","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7243689867","display_name":null,"funder_award_id":"2020XD-A07-1","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2560674852","https://openalex.org/W2741928062","https://openalex.org/W2747329762","https://openalex.org/W2905471643","https://openalex.org/W2951525151","https://openalex.org/W2951615109","https://openalex.org/W2952768212","https://openalex.org/W2963777632","https://openalex.org/W2964105864","https://openalex.org/W2964212344","https://openalex.org/W2964349647","https://openalex.org/W2971013448","https://openalex.org/W2971136144","https://openalex.org/W2997591266","https://openalex.org/W3035053871","https://openalex.org/W3114986498"],"related_works":["https://openalex.org/W2162899405","https://openalex.org/W3113091479","https://openalex.org/W941090075","https://openalex.org/W2044987316","https://openalex.org/W3208297503","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353"],"abstract_inverted_index":{"Few-shot":[0],"relation":[1,8,25,92],"extraction":[2],"(FSRE)":[3],"aims":[4],"to":[5,33,66,95,149,169,196],"predict":[6],"the":[7,39,96,135,157,163,177,201,206,210,214,240,251,259,279],"for":[9,23,116],"a":[10,15,19,79,121,141,183,219],"pair":[11,105],"of":[12,46,64,82,218,281],"entities":[13,90],"in":[14,209],"sentence":[16,220,252],"by":[17,37,154,264],"exploring":[18],"few":[20,72],"labeled":[21],"instances":[22],"each":[24,170],"type.":[26],"Current":[27],"methods":[28,54],"mainly":[29],"rely":[30],"on":[31,43,70,103,274],"meta-learning":[32,65],"learn":[34,67,110,197],"generalized":[35],"representations":[36,69,115,153,166],"optimizing":[38],"network":[40,189,216],"parameters":[41,207],"based":[42],"various":[44],"collections":[45],"tasks":[47],"sampled":[48,77],"from":[49,57,78,156],"training":[50,73,98,159,266],"data.":[51,85],"However,":[52],"these":[53],"may":[55],"suffer":[56],"two":[58,275],"main":[59],"issues.":[60],"1)":[61],"Insufficient":[62],"supervision":[63],"discriminative":[68,112,152],"very":[71],"instances,":[74,160],"which":[75,146],"are":[76,167,203],"large":[80],"amount":[81],"base":[83],"class":[84],"2)":[86],"Spurious":[87],"correlations":[88,261],"between":[89,242],"and":[91,113,128,130,172,186,222,229,245,247],"types":[93],"due":[94],"biased":[97,265],"procedure":[99],"that":[100,162],"focuses":[101],"more":[102,111,151],"entity":[104,224,230,236,243],"rather":[106],"than":[107],"context.":[108],"To":[109],"unbiased":[114,198],"FSRE,":[117],"this":[118],"paper":[119],"proposes":[120],"two-stage":[122],"approach":[123],"via":[124],"supervised":[125,142],"contrastive":[126,143],"learning":[127,155],"sentence-":[129,185],"entity-level":[131,187],"prototypical":[132,188],"networks.":[133],"In":[134,176],"first":[136,211],"(pre-training)":[137],"stage,":[138,180],"we":[139,181],"introduce":[140],"pre-training":[144],"method,":[145],"is":[147],"able":[148],"yield":[150],"entire":[158,227],"such":[161],"semantically":[164],"related":[165],"close":[168],"other,":[171],"far":[173],"away":[174],"otherwise.":[175],"second":[178],"(meta-learning)":[179],"propose":[182],"novel":[184],"equipped":[190],"with":[191,205],"fine-grained":[192],"feature-wise":[193],"fusion":[194],"strategy":[195],"representations,":[199],"where":[200],"networks":[202],"initialized":[204],"trained":[208],"stage.":[212],"Specifically,":[213],"proposed":[215],"consists":[217],"branch":[221,237],"an":[223],"branch,":[225],"taking":[226],"sentences":[228],"mentions":[231],"as":[232],"inputs,":[233],"respectively.":[234],"The":[235],"explicitly":[238],"captures":[239],"correlation":[241],"pairs":[244],"relations,":[246],"then":[248],"dynamically":[249],"adjusts":[250],"branch's":[253],"prediction":[254],"distributions.":[255],"By":[256],"doing":[257],"so,":[258],"spurious":[260],"issue":[262],"caused":[263],"samples":[267],"can":[268],"be":[269],"properly":[270],"mitigated.":[271],"Extensive":[272],"experiments":[273],"FSRE":[276],"benchmarks":[277],"demonstrate":[278],"effectiveness":[280],"our":[282],"approach.":[283]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}