{"id":"W3034445880","doi":"10.18653/v1/2020.acl-main.102","title":"Dynamic Memory Induction Networks for Few-Shot Text Classification","year":2020,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Generalization; Artificial intelligence; Process (computing); Adaptive routing; Machine learning; Mechanism (biology); Dynamic random-access memory; Routing (electronic design automation); Routing protocol","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002026818,0.00009884841,0.0001009227,0.00004896806,0.0001562848,0.0001588155,0.0003597222,0.00007248366,0.00005992066],"category_scores_gemma":[0.00007500812,0.0000949047,0.0000585126,0.0003611665,0.00002315498,0.0004430895,0.00005627254,0.0001403143,0.0000940705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003900555,"about_ca_system_score_gemma":0.00003820018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003903168,"about_ca_topic_score_gemma":0.000004956501,"domain_scores_codex":[0.9990534,0.00004730951,0.0002002648,0.0003568359,0.0001512022,0.0001910383],"domain_scores_gemma":[0.9994096,0.00007994838,0.00009605146,0.0002183546,0.00007730506,0.000118793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004304229,0.00005862289,0.00008924476,0.00002892993,0.00003031296,0.000001846303,0.002415053,0.03409496,0.007662252,0.1416687,0.009929961,0.8039771],"study_design_scores_gemma":[0.0002851822,0.000063982,0.002594423,0.000003320402,0.000003670189,0.000002346738,0.0003650051,0.9797533,0.00008956344,0.0003800759,0.0163329,0.0001262925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001332875,0.0000405937,0.9802052,0.009268806,0.0003814856,0.0002492308,3.959856e-7,0.0003429643,0.008178464],"genre_scores_gemma":[0.9234773,0.00001063703,0.0722611,0.00291159,0.0001131154,0.00003601437,0.00001686491,0.00001155085,0.001161849],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9456583,"threshold_uncertainty_score":0.3870102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06928187749799837,"score_gpt":0.2839225347854978,"score_spread":0.2146406572874995,"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."}}