{"id":"https://openalex.org/W4312107645","doi":"https://doi.org/10.48550/arxiv.2212.10823","title":"Continual Contrastive Finetuning Improves Low-Resource Relation Extraction","display_name":"Continual Contrastive Finetuning Improves Low-Resource Relation Extraction","publication_year":2022,"publication_date":"2022-12-21","ids":{"openalex":"https://openalex.org/W4312107645","doi":"https://doi.org/10.48550/arxiv.2212.10823"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2212.10823","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.10823","pdf_url":"https://arxiv.org/pdf/2212.10823","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2212.10823","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080937886","display_name":"Wenxuan Zhou","orcid":"https://orcid.org/0000-0003-1199-885X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhou, Wenxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394046","display_name":"Sheng Zhang","orcid":"https://orcid.org/0000-0003-1732-0011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Sheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023123863","display_name":"Tristan Naumann","orcid":"https://orcid.org/0000-0003-2150-1747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naumann, Tristan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102861481","display_name":"Muhao Chen","orcid":"https://orcid.org/0000-0003-0118-3147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Muhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019494985","display_name":"Hoifung Poon","orcid":"https://orcid.org/0000-0002-9067-0918"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Poon, Hoifung","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080937886"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9621000289916992,"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":0.8209750652313232},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.7176588773727417},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.6924628615379333},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6482911109924316},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6407113671302795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5668759346008301},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47599923610687256},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4669647514820099},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4627722501754761},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45857149362564087},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42909014225006104},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.25768375396728516},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.22602930665016174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209750652313232},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7176588773727417},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.6924628615379333},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6482911109924316},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6407113671302795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5668759346008301},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47599923610687256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4669647514820099},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4627722501754761},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45857149362564087},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42909014225006104},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.25768375396728516},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22602930665016174},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2212.10823","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.10823","pdf_url":"https://arxiv.org/pdf/2212.10823","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2212.10823","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2212.10823","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2212.10823","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.10823","pdf_url":"https://arxiv.org/pdf/2212.10823","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W2169074127","https://openalex.org/W83146503","https://openalex.org/W2163707935","https://openalex.org/W202723009","https://openalex.org/W2145955964","https://openalex.org/W2188612292","https://openalex.org/W2165396616","https://openalex.org/W2058882606"],"abstract_inverted_index":{"Relation":[0],"extraction":[1],"(RE),":[2],"which":[3,63],"has":[4,13,24],"relied":[5],"on":[6,45,140,171],"structurally":[7],"annotated":[8],"corpora":[9],"for":[10],"model":[11,67,93],"training,":[12],"been":[14],"particularly":[15],"challenging":[16],"in":[17,61,73,101,115],"low-resource":[18,26],"scenarios":[19],"and":[20,43,85,89,146,169],"domains.":[21],"Recent":[22],"literature":[23],"tackled":[25],"RE":[27,66,92,143,165],"by":[28,40,48,167],"self-supervised":[29],"learning,":[30],"where":[31],"the":[32,36,59,65,71,83,91,116,149,172],"solution":[33],"involves":[34],"pretraining":[35],"entity":[37],"pair":[38],"embedding":[39],"RE-based":[41],"objective":[42],"finetuning":[44],"labeled":[46],"data":[47],"classification-based":[49],"objective.":[50],"However,":[51],"a":[52,122],"critical":[53],"challenge":[54],"to":[55,87,130,134],"this":[56,77,102],"approach":[57],"is":[58],"gap":[60,84],"objectives,":[62],"prevents":[64],"from":[68],"fully":[69],"utilizing":[70],"knowledge":[72],"pretrained":[74],"representations.":[75],"In":[76],"paper,":[78],"we":[79,119],"aim":[80],"at":[81],"bridging":[82],"propose":[86,121],"pretrain":[88],"finetune":[90],"using":[94,156],"consistent":[95],"objectives":[96],"of":[97,104,151],"contrastive":[98,124],"learning.":[99],"Since":[100],"kind":[103],"representation":[105,117],"learning":[106],"paradigm,":[107],"one":[108,128],"relation":[109,129],"may":[110],"easily":[111],"form":[112,131],"multiple":[113,132],"clusters":[114,133],"space,":[118],"further":[120],"multi-center":[123],"loss":[125],"that":[126],"allows":[127],"better":[135],"align":[136],"with":[137],"pretraining.":[138],"Experiments":[139],"two":[141,173],"document-level":[142],"datasets,":[144,174],"BioRED":[145],"Re-DocRED,":[147],"demonstrate":[148],"effectiveness":[150],"our":[152,161],"method.":[153],"Particularly,":[154],"when":[155],"1%":[157],"end-task":[158],"training":[159],"data,":[160],"method":[162],"outperforms":[163],"PLM-based":[164],"classifier":[166],"10.5%":[168],"6.1%":[170],"respectively.":[175]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2023-01-04T00:00:00"}