{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000678147,0.0001223269,0.0001217939,0.0002489742,0.0001358256,0.0001562801,0.001601645,0.00007267865,0.00001033042],"category_scores_gemma":[0.0002125645,0.0001076628,0.00004416758,0.0007771654,0.00001478373,0.0003522187,0.000398773,0.00009179014,0.000111476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003798078,"about_ca_system_score_gemma":0.0001588153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003441554,"about_ca_topic_score_gemma":0.00003136991,"domain_scores_codex":[0.9985652,0.00004402616,0.0002290221,0.0006792393,0.0001907199,0.0002917774],"domain_scores_gemma":[0.9976764,0.0002482961,0.0000643504,0.001828036,0.0001096539,0.0000733177],"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":[0.00001425019,0.0001191208,0.0001728089,0.00008208445,0.00001418172,0.000001910375,0.0002442694,0.0005893598,0.007757639,0.2511322,0.01359358,0.7262786],"study_design_scores_gemma":[0.0004086047,0.00005433133,0.0009887601,0.00001412879,0.000005223652,3.064374e-7,0.00002114542,0.9918815,0.0009385082,0.001711012,0.003837855,0.000138622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004047748,0.00002114725,0.9883753,0.002671969,0.000468214,0.000380474,0.00001912814,0.0008111878,0.003204855],"genre_scores_gemma":[0.8721078,0.000004393982,0.1260773,0.0004873133,0.00008461772,0.00007498204,0.0001611279,0.00001699974,0.0009854499],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9912921,"threshold_uncertainty_score":0.4390361,"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."}}