{"id":"W4386576747","doi":"10.18653/v1/2023.findings-eacl.171","title":"ICA-Proto: Iterative Cross Alignment Prototypical Network for Incremental Few-Shot Relation Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"National Key Research and Development Program of China","keywords":"Computer science; Benchmark (surveying); Embedding; Relation (database); Representation (politics); Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Iterative and incremental development; Encoding (memory); Feature vector; Machine learning; Feature learning; Data mining","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0008608935,0.0001460051,0.0001326035,0.00008310437,0.0004417281,0.0004020277,0.0003589068,0.00008947336,0.0000904052],"category_scores_gemma":[0.00008699747,0.0001331714,0.00007860058,0.0006092806,0.00004907517,0.0006023998,0.0001264039,0.0001271552,0.0003087955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001112443,"about_ca_system_score_gemma":0.00005429586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005416631,"about_ca_topic_score_gemma":0.000004140306,"domain_scores_codex":[0.9982802,0.0001259008,0.0003730521,0.0004804374,0.0003701137,0.0003702432],"domain_scores_gemma":[0.9991319,0.0001945322,0.0001400856,0.000313794,0.0001166239,0.0001031251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001764791,0.0001211404,0.01838152,0.00004101338,0.00005320113,0.000004490033,0.002700385,0.008753,0.004265119,0.923444,0.01308717,0.02897254],"study_design_scores_gemma":[0.001051196,0.0002327446,0.155462,0.000028155,0.000004716283,0.000002856577,0.0001926246,0.8015648,0.001204352,0.007593086,0.03239521,0.0002683108],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01131028,0.000006841622,0.9738469,0.001791175,0.0003586293,0.003312862,0.00000347232,0.0006087478,0.008761116],"genre_scores_gemma":[0.8855402,0.000004200708,0.1066307,0.0006806339,0.0002439152,0.002684112,0.0001403824,0.00002063287,0.004055215],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9158509,"threshold_uncertainty_score":0.5430571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08793856194669883,"score_gpt":0.3498732966632659,"score_spread":0.261934734716567,"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."}}