{"id":"W4379521537","doi":"10.21428/594757db.62395a61","title":"Towards Improving Text Classification Tasks Based on Knowledge Graphs for Limited Labeled Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Knowledge graph; Transformer; Artificial intelligence; Domain knowledge; Machine learning; Language model; Graph; Training set; Labeled data; Natural language processing; Process (computing); Data mining; Theoretical computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002647855,0.002305337,0.001443462,0.003953133,0.0008176235,0.00164638,0.003024414,0.002414041,0.002055734],"category_scores_gemma":[0.01110969,0.0006952864,0.001907358,0.003070726,0.0008650281,0.00756911,0.002073395,0.003109184,0.002363911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001546472,"about_ca_system_score_gemma":0.001590236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01138229,"about_ca_topic_score_gemma":0.01558751,"domain_scores_codex":[0.9983897,0.0005478265,0.0001063186,0.0005482849,0.0002777998,0.000130145],"domain_scores_gemma":[0.9899306,0.006820031,0.0005140824,0.001577219,0.0008733785,0.0002846676],"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":[0.0006994617,0.0009331952,0.00618938,0.0004340462,0.0002498224,0.0004008636,0.0003782711,0.3188317,0.01518559,0.006557016,0.02370655,0.6264341],"study_design_scores_gemma":[0.00002449996,0.0000372938,0.0003374133,0.00001383596,0.00002763487,0.00003194455,0.00004562808,0.9884707,0.002793028,0.007167258,0.001040449,0.00001036374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09416654,0.001871923,0.8752679,0.001145346,0.0001574925,0.000310253,0.001914544,0.02217671,0.002989292],"genre_scores_gemma":[0.5468317,0.0008135418,0.4344576,0.000869255,0.0002369636,0.0004357734,0.01116219,0.0007954816,0.004397529],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01138229,"threshold_uncertainty_score":0.02263206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1388202731800211,"score_gpt":0.3311601625890719,"score_spread":0.1923398894090508,"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."}}