{"id":"W4401042328","doi":"10.18653/v1/2024.naacl-long.30","title":"DuRE: Dual Contrastive Self Training for Semi-Supervised Relation Extraction","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dual (grammatical number); Computer science; Relationship extraction; Relation (database); Artificial intelligence; Training (meteorology); Extraction (chemistry); Natural language processing; Pattern recognition (psychology); Data mining; Chromatography; Linguistics; Chemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002643964,0.001798184,0.001286975,0.002360938,0.001077545,0.001952049,0.003249622,0.002173614,0.01230992],"category_scores_gemma":[0.005656373,0.001157551,0.001529871,0.001571774,0.0007419162,0.00411137,0.002849666,0.002902207,0.01188425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006322972,"about_ca_system_score_gemma":0.001216813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002638735,"about_ca_topic_score_gemma":0.00946822,"domain_scores_codex":[0.998185,0.0005130409,0.0001384698,0.0007601441,0.0002821925,0.0001210307],"domain_scores_gemma":[0.9964276,0.002052957,0.0001221935,0.0008468817,0.0004338507,0.0001165984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008715932,0.0005167556,0.002093409,0.0005575747,0.0003218999,0.0002972111,0.0004062617,0.01360521,0.03307139,0.006141223,0.09165961,0.8504579],"study_design_scores_gemma":[0.0002136484,0.000377206,0.00227311,0.0001094963,0.0001373206,0.0004544567,0.0002381249,0.8908845,0.04243151,0.01875013,0.04404571,0.00008489341],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02260987,0.00153388,0.8854806,0.0003744313,0.0004547755,0.0003399087,0.00423746,0.0798871,0.005081808],"genre_scores_gemma":[0.1736972,0.0004981536,0.7790847,0.0006272644,0.0002527204,0.0008103505,0.02702092,0.003885717,0.01412302],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01230992,"threshold_uncertainty_score":0.04118073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04646948887432286,"score_gpt":0.289196637814587,"score_spread":0.2427271489402641,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}